© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11891
    Prev
    Next
    INDEX
    Explanations

    fragments of text coming from Law, technical documentation, and formal writing

    oai_token-act-pair · gemini-2.0-flash

    programming/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MigrationBuilder
    -0.82
    تقاوى
    -0.81
     typelib
    -0.78
     Signalez
    -0.73
     للاسماء
    -0.71
     kasarigan
    -0.70
     PeEnEo
    -0.70
    :✨
    -0.69
    ImageContext
    -0.68
    aarrggbb
    -0.67
    POSITIVE LOGITS
    ticon
    0.48
    ấn
    0.46
    LETED
    0.46
     momento
    0.45
    Externí
    0.44
     wilayah
    0.43
    lerc
    0.43
    proses
    0.43
    getItems
    0.41
    uette
    0.41
    Activations Density 4.318%

    No Known Activations