© 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. 11028
    Prev
    Next
    INDEX
    Explanations

    phrases related to proportions, percentages, and measurements, particularly within scientific or technical documentation.

    oai_token-act-pair · gemini-2.0-flash

    weight

    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
     tissu
    -0.48
    тут
    -0.48
    orov
    -0.46
     nakalista
    -0.46
    ote
    -0.45
     suscripción
    -0.45
    ʺ
    -0.44
     known
    -0.44
    minify
    -0.42
     para
    -0.42
    POSITIVE LOGITS
     linkovi
    0.91
     Percent
    0.74
     percent
    0.72
    %";
    0.69
    %");
    0.68
    intele
    0.67
    migrationBuilder
    0.66
    Tikang
    0.65
     PERCENT
    0.63
    percent
    0.63
    Activations Density 1.857%

    No Known Activations