© 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. 12104
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to sports and competition

    oai_token-act-pair · gemini-2.0-flash

    Sports/games context

    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
    SequentialGroup
    -0.84
    ftagPool
    -0.82
    endphp
    -0.75
     tartalomajánló
    -0.74
    UnsafeEnabled
    -0.73
     ModelExpression
    -0.72
    IsMutable
    -0.70
    EndGlobalSection
    -0.69
     дописавши
    -0.67
    Jeografia
    -0.66
    POSITIVE LOGITS
    isle
    0.44
     thiệu
    0.44
     Assn
    0.44
    guys
    0.43
    ểu
    0.43
     iya
    0.42
    ArgumentParser
    0.42
    estars
    0.42
    Instru
    0.41
     attendre
    0.41
    Activations Density 4.794%

    No Known Activations