© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3829
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams, players, and statistics

    oai_token-act-pair · gemini-2.0-flash

    sports statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     GenerationType
    -0.71
    insee
    -0.62
     ***!
    -0.62
    windowFixed
    -0.57
    Personendaten
    -0.57
    RenderAtEndOf
    -0.57
    protoimpl
    -0.56
     ModelRenderer
    -0.56
     drafted
    -0.55
     roster
    -0.55
    POSITIVE LOGITS
     NKC
    0.56
    providedIn
    0.53
    ifest
    0.52
    chism
    0.51
    acorn
    0.51
    Train
    0.50
     Britann
    0.49
     train
    0.49
    onActivityResult
    0.49
    NgModule
    0.48
    Activations Density 2.527%

    No Known Activations