© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46409
    Prev
    Next
    INDEX
    Explanations

    date

    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_10_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
    ↵
    0.77
     njegova
    0.76
    AS
    0.75
     hangi
    0.70
     kif
    0.69
     badger
    0.68
    ও
    0.68
     corticoster
    0.66
     propria
    0.66
     เหรอ
    0.65
    POSITIVE LOGITS
     Dates
    0.90
    ll
    0.89
    name
    0.88
    Ра
    0.83
    h
    0.80
    dates
    0.79
     Internacional
    0.76
     Date
    0.75
    ၊
    0.72
    bibfnamefont
    0.72
    Activations Density 0.023%

    No Known Activations