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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12663
    Prev
    Next
    INDEX
    Explanations

    semicolons, curly brackets, parentheses, quotes, and plus signs frequently found in code.

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    uidado
    -0.69
     Efq
    -0.69
    "]];
    -0.66
    zyw
    -0.63
    ientras
    -0.63
    )");
    -0.63
     Fid
    -0.62
     cherchés
    -0.61
    ^(@)
    -0.61
    __':
    -0.60
    POSITIVE LOGITS
     intptr
    0.57
    msubsup
    0.55
    item
    0.54
    matchCondition
    0.54
    protoimpl
    0.53
    //
    0.52
    triangleq
    0.49
    ;#
    0.49
    endphp
    0.47
    hasMoreElements
    0.47
    Activations Density 0.429%

    No Known Activations