© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4947
    Prev
    Next
    INDEX
    Explanations

    Australian Rules Football and Gaelic football

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    頭
    0.36
    מע
    0.36
    юз
    0.36
     proz
    0.36
    uzi
    0.35
    舵
    0.34
    <0x9B>
    0.34
     OI
    0.34
    ุ้น
    0.34
     nope
    0.33
    POSITIVE LOGITS
     AFL
    0.86
     Gaelic
    0.61
     GAA
    0.61
     hurling
    0.57
     afl
    0.51
     NAB
    0.47
     Collingwood
    0.45
     Swans
    0.45
    🏐
    0.43
     GA
    0.43
    Activations Density 0.004%

    No Known Activations