© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 3610
    Prev
    Next
    INDEX
    Explanations

    golf

    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_38_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
     sali
    0.42
    ServiceObject
    0.39
    ною
    0.39
    RAIT
    0.39
     shad
    0.38
     为
    0.37
     lanç
    0.37
     Herzeg
    0.37
     Rowland
    0.36
    羰
    0.36
    POSITIVE LOGITS
     golf
    1.13
     golfers
    1.12
    Golf
    0.99
     golfer
    0.99
    golf
    0.97
     PGA
    0.95
     Golf
    0.94
     golfing
    0.91
    🏌
    0.86
    ゴルフ
    0.85
    Activations Density 0.012%

    No Known Activations