© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15869
    Prev
    Next
    INDEX
    Explanations

    parentheses and curly braces in computer code, especially when nested

    oai_token-act-pair · gemini-2.0-flash

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    )");
    -1.16
    ")));
    -1.15
    '));
    -1.09
    "]);
    -1.09
    "]];
    -1.08
     "));
    -1.07
    "]));
    -1.06
    ]))
    -1.05
     Мексичка
    -1.05
    )");
    -1.05
    POSITIVE LOGITS
    (
    1.87
     (
    1.43
    （
    1.13
    [
    1.12
    (\
    0.79
    re
    0.75
    v
    0.73
     [
    0.71
    <bos>
    0.69
    <h6>
    0.68
    Activations Density 1.644%

    No Known Activations