© 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. 10005
    Prev
    Next
    INDEX
    Explanations

    words related to sports seasons, games, and scoring

    oai_token-act-pair · gemini-2.0-flash

    sports season

    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
    ergies
    -0.73
     المعيارى
    -0.73
     CallOverrides
    -0.66
     Waray
    -0.66
    hoeddwyd
    -0.64
    rolid
    -0.63
    MigrationBuilder
    -0.63
    dataclass
    -0.62
    #
    -0.62
    ApiProperty
    -0.61
    POSITIVE LOGITS
    第一天
    0.48
     truncated
    0.47
     arrivant
    0.47
    셜
    0.44
     nuovo
    0.43
     start
    0.43
     Jurí
    0.42
    ValueStyle
    0.42
     starts
    0.41
     nový
    0.41
    Activations Density 0.813%

    No Known Activations