© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8831
    Prev
    Next
    INDEX
    Explanations

    SUV descriptions

    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_13_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
     دنوں
    0.51
     चाहिये
    0.51
    ępnie
    0.51
     Süden
    0.50
    呔
    0.50
    เมตร
    0.49
     형태
    0.49
    ভিতে
    0.49
     quién
    0.49
     igjen
    0.49
    POSITIVE LOGITS
     C
    0.57
     For
    0.56
     W
    0.55
    ↵↵
    0.54
     can
    0.53
     Polar
    0.53
     espèce
    0.52
     Intermediate
    0.52
     they
    0.51
     Virgin
    0.51
    Activations Density 0.001%

    No Known Activations