© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9422
    Prev
    Next
    INDEX
    Explanations

    words related to soccer with an emphasis on the English Premier League

    oai_token-act-pair · gemini-2.0-flash

    soccer players

    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
    Negative Logits
     onCreateView
    -0.98
    StoryboardSegue
    -0.82
    findpost
    -0.81
     onAnimation
    -0.81
    migrationBuilder
    -0.80
     utafitiHapana
    -0.79
    endphp
    -0.77
     ModelExpression
    -0.76
     resourceCulture
    -0.74
    tvguidetime
    -0.74
    POSITIVE LOGITS
     démocratique
    0.48
    setTarget
    0.43
     intérieure
    0.42
    glTexCoord
    0.41
    kurat
    0.41
    gebouw
    0.40
     étrangère
    0.40
     sicura
    0.40
    žius
    0.39
     pair
    0.39
    Activations Density 0.566%

    No Known Activations