© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7753
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and athletic positions

    oai_token-act-pair · gemini-2.0-flash

    football

    np_max-act-logits · gemini-2.0-flash

    country adjectives

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     hockey
    -1.07
     basketball
    -1.04
    Hockey
    -0.98
    basketball
    -0.96
     cricket
    -0.96
    hockey
    -0.96
     volleyball
    -0.95
     Volleyball
    -0.94
     Hockey
    -0.93
     Basketball
    -0.93
    POSITIVE LOGITS
     foot
    0.60
    cal
    0.58
     American
    0.56
     AssemblyCulture
    0.55
     cal
    0.53
    foot
    0.53
    principalColumn
    0.52
    ️
    0.52
     association
    0.49
    のだ
    0.48
    Activations Density 2.072%

    No Known Activations