© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13114
    Prev
    Next
    INDEX
    Explanations

    a very diverse collection of terms, including locations, companies, words that are part of formal names, some political and medical terms, and words related to film

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or specific phrases in programming or metadata

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash

    say "second words"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ejus
    -0.60
     quæ
    -0.50
    ym
    -0.49
    dol
    -0.49
    ow
    -0.46
    wi
    -0.46
     Inscrivez
    -0.46
     kym
    -0.44
     omnia
    -0.44
    id
    -0.44
    POSITIVE LOGITS
     ModelExpression
    1.48
     autorytatywna
    1.30
    IntoConstraints
    1.28
     متعلقه
    1.27
     AssemblyCulture
    1.24
    RenderAtEndOf
    1.21
     Audiodateien
    1.20
     typelib
    1.18
    InputBorder
    1.17
     дописавши
    1.16
    Activations Density 5.907%

    No Known Activations