© 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. 1016
    Prev
    Next
    INDEX
    Explanations

    mentions of tennis players taking part in the Australian Open mixed doubles

    oai_token-act-pair · gemini-2.0-flash

    Tennis

    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
     Golf
    -1.37
     golf
    -1.37
     tennis
    -1.32
     Tennis
    -1.29
    Golf
    -1.27
    golf
    -1.23
    Tennis
    -1.20
     GOLF
    -1.19
    tennis
    -1.19
     golfing
    -1.03
    POSITIVE LOGITS
    ěn
    0.56
    esgue
    0.56
    __*/
    0.52
    WebElementEntity
    0.49
    üyada
    0.49
    وعة
    0.47
    ddots
    0.46
     dinam
    0.45
    Ẻ
    0.45
     Ste
    0.44
    Activations Density 2.035%

    No Known Activations