© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1559
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports

    oai_token-act-pair · gemini-2.0-flash

    terms related to scoring in sports

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

    goals and scoring

    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
    Negative Logits
    NewReader
    -0.60
     deportivos
    -0.50
    tinyos
    -0.49
    ători
    -0.48
    azan
    -0.46
     afili
    -0.45
    ;">
    -0.45
    cable
    -0.45
    ู่
    -0.44
    álva
    -0.44
    POSITIVE LOGITS
     goals
    1.56
     goal
    1.45
     scoring
    1.34
     Goals
    1.32
    goals
    1.30
    Goals
    1.28
    goal
    1.18
     scored
    1.17
     Scoring
    1.16
    Scoring
    1.13
    Activations Density 5.201%

    No Known Activations