© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2064
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming jargon

    oai_token-act-pair · gemini-2.0-flash

    the word "to" in various languages

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

    foreign "that"

    np_max-act-logits · gemini-2.0-flash
    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
    aux
    -0.40
    /-/
    -0.36
    urs
    -0.35
    gat
    -0.35
    geb
    -0.34
    ện
    -0.33
     aux
    -0.33
     Der
    -0.33
     gat
    -0.33
    ্ন
    -0.32
    POSITIVE LOGITS
     чтобы
    1.68
     để
    1.52
     щоб
    1.49
     to
    1.30
     чтоб
    1.27
    Чтоб
    1.23
     upang
    1.23
     untuk
    1.19
     żeby
    1.19
     Чтобы
    1.16
    Activations Density 0.579%

    No Known Activations