© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    words related to American football, especially statistics like yards, touchdowns, and positions

    oai_token-act-pair · gemini-2.0-flash

    yards

    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
    yard
    -1.61
     yards
    -1.61
     yard
    -1.52
    yards
    -1.32
     Yard
    -1.20
    Yard
    -1.19
     Yards
    -1.17
    YARD
    -1.13
    <bos>
    -0.96
     yds
    -0.80
    POSITIVE LOGITS
     FetchType
    0.68
    featureID
    0.65
     CiNii
    0.62
     ceramica
    0.61
     femelle
    0.60
    bcrypt
    0.59
    حوالہ
    0.59
    󠁮
    0.58
    ModelSerializer
    0.58
    ppuden
    0.57
    Activations Density 5.096%

    No Known Activations