© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13862
    Prev
    Next
    INDEX
    Explanations

    mathematical and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    equations and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ValueStyle
    -1.33
    parsedMessage
    -1.16
    contentLoaded
    -1.09
     kasarigan
    -1.08
     autorytatywna
    -1.07
    LookAnd
    -1.05
    NameInMap
    -1.04
    IndentedString
    -1.04
     estekak
    -1.00
    RenderAtEndOf
    -1.00
    POSITIVE LOGITS
     détru
    0.44
     مُعرِّف
    0.43
     scatola
    0.42
     întâ
    0.42
    ্ব
    0.40
     prati
    0.40
    området
    0.40
    是以
    0.39
     quæ
    0.39
     Mourning
    0.39
    Activations Density 85.367%

    No Known Activations