© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 627
    Prev
    Next
    INDEX
    Explanations

    words and phrases loosely related to common features of populations, diseases, and opinions

    oai_token-act-pair · gemini-2.0-flash

    characteristics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    LEncoder
    -0.98
    writeFieldEnd
    -0.90
     Normdatei
    -0.85
    ValueStyle
    -0.84
    MigrationBuilder
    -0.83
    %");
    -0.81
    UrlResolution
    -0.80
    %";
    -0.79
     Theſe
    -0.79
    новниш
    -0.77
    POSITIVE LOGITS
    <sup>
    0.51
    â
    0.49
    B
    0.49
    好
    0.48
    b
    0.48
    multer
    0.48
    <i>
    0.46
    ok
    0.46
    <em>
    0.45
    <h1>
    0.45
    Activations Density 1.300%

    No Known Activations