© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63275
    Prev
    Next
    INDEX
    Explanations

    Bach, Australia

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     থাকত
    0.49
     sería
    0.47
     থাকিত
    0.46
    ନ୍ଦ
    0.45
     serait
    0.43
     Would
    0.42
     wäre
    0.42
    ဿ
    0.41
    yat
    0.41
     would
    0.39
    POSITIVE LOGITS
     mut
    0.46
    বাধ
    0.45
    Bach
    0.43
    Australia
    0.40
     Perpetual
    0.40
     Bach
    0.39
     Gloucestershire
    0.38
    Dual
    0.37
    João
    0.37
    Mut
    0.36
    Activations Density 0.000%

    No Known Activations