© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11086
    Prev
    Next
    INDEX
    Explanations

    words related to winning competitions

    oai_token-act-pair · gemini-2.0-flash

    winner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     winner
    -2.38
     winners
    -1.97
    winner
    -1.96
     Winner
    -1.93
    Winner
    -1.85
    winners
    -1.62
     Winners
    -1.53
    Winners
    -1.45
     WINNER
    -1.44
     ganador
    -1.37
    POSITIVE LOGITS
     GIPHY
    0.71
    stateProvider
    0.68
    routeProvider
    0.67
     Moq
    0.59
     Biôgrafia
    0.56
     Kershaw
    0.56
    setLayoutManager
    0.55
    Orsay
    0.55
     INVEST
    0.54
    GenerationType
    0.54
    Activations Density 1.810%

    No Known Activations