© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 773
    Prev
    Next
    INDEX
    Explanations

    a variety of programming tokens, logical keywords, and other code-related terms

    oai_token-act-pair · gemini-2.0-flash

    code/legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Vikipedi
    -0.77
    存于互联网档案馆
    -0.73
    ритори
    -0.71
    httphttps
    -0.71
    ِّف
    -0.69
    TypedDataSet
    -0.65
    ɵɵelementEnd
    -0.65
    Revenir
    -0.62
    InputBorder
    -0.62
    Становништво
    -0.61
    POSITIVE LOGITS
    ↵↵
    0.49
    ))){
    0.46
    <eos>
    0.46
    ]){
    0.45
    もありました
    0.44
    nipeg
    0.44
     sobě
    0.41
    ➽
    0.41
    %"),
    0.41
    "));
    0.40
    Activations Density 2.001%

    No Known Activations