© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    code syntax, including assignment, object access, and array indexing.

    oai_token-act-pair · gemini-2.0-flash

    file extensions or function-like terms

    np_token-act-pair-logits · gpt-4o-mini
    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
    InputBorder
    -0.65
    FTFY
    -0.65
    '])){
    -0.62
    amaño
    -0.61
    ")));
    -0.60
    ModelSerializer
    -0.59
    SEGUIR
    -0.59
    حوالہ
    -0.57
    aarrggbb
    -0.56
    .
    -0.56
    POSITIVE LOGITS
    com
    0.71
    exe
    0.70
    js
    0.69
    off
    0.64
    get
    0.63
    TypedDataSet
    0.63
    c
    0.63
    p
    0.63
    py
    0.62
    txt
    0.62
    Activations Density 7.547%

    No Known Activations