© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3348
    Prev
    Next
    INDEX
    Explanations

    words and phrases heavily involved in sports reporting.

    oai_token-act-pair · gemini-2.0-flash

    programming terms or identifiers

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

    sports matches

    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
    üste
    -0.46
     extranjero
    -0.44
    varargin
    -0.44
     Públicas
    -0.43
     varargin
    -0.42
     đốc
    -0.40
    ebaran
    -0.40
     tả
    -0.39
     brancas
    -0.39
    — 
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    1.17
    IntoConstraints
    0.91
    ollectionView
    0.79
    RegressionTest
    0.73
    NOPQRST
    0.71
    ArgumentParser
    0.70
    VersionUID
    0.67
    RenderAtEndOf
    0.66
    ंदीखरीदारी
    0.66
     continúas
    0.63
    Activations Density 0.790%

    No Known Activations