© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10422
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    Negative Logits
     Gm
    0.39
     Squire
    0.36
    Gm
    0.36
     sixth
    0.35
     রিপোর্টে
    0.35
     produziert
    0.35
    事务所
    0.35
     Chestnut
    0.35
    洼
    0.34
     ತಿಳ
    0.34
    POSITIVE LOGITS
    半
    0.57
     चालीस
    0.55
     half
    0.55
     Half
    0.53
    Half
    0.53
    half
    0.50
     forty
    0.50
     veinte
    0.50
    二十
    0.49
     চল্লিশ
    0.47
    Activations Density 0.055%

    No Known Activations