© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33872
    Prev
    Next
    INDEX
    Explanations

    Gel, Ford, Jelly Roll

    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_3_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
    n
    1.10
    p
    0.97
    ad
    0.95
    ین
    0.89
    на
    0.83
    น
    0.83
    ла
    0.79
    न
    0.78
    ン
    0.77
    н
    0.72
    POSITIVE LOGITS
     omp
    0.63
     GEL
    0.61
    ’
    0.61
    jší
    0.59
     del
    0.58
    RI
    0.57
     gel
    0.57
     slog
    0.55
     Gel
    0.54
    AJ
    0.54
    Activations Density 0.003%

    No Known Activations