© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6552
    Prev
    Next
    INDEX
    Explanations

    language related to sports, specifically soccer

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming references

    np_token-act-pair-logits · gpt-4o-mini

    soccer/MLS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Football
    -0.53
    matchCondition
    -0.50
    uteness
    -0.47
     football
    -0.45
     estekak
    -0.45
    zenio
    -0.45
    Football
    -0.44
     barrels
    -0.44
    football
    -0.43
    diali
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.60
    featureID
    0.60
     travaillons
    0.54
    migrationBuilder
    0.54
     pymysql
    0.54
    VideoCapture
    0.54
     näytte
    0.54
     unknownFields
    0.52
    cmu
    0.52
    блиоте
    0.52
    Activations Density 1.258%

    No Known Activations