© 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. 8603
    Prev
    Next
    INDEX
    Explanations

    SQL, code, and foreign words

    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
    Negative Logits
    -
    0.76
    t
    0.76
    s
    0.68
    ା
    0.58
    ا
    0.55
    -}
    0.55
    commision
    0.54
     توضیح
    0.54
    :')
    0.53
     ആൻ
    0.52
    POSITIVE LOGITS
     hood
    0.57
     کړ
    0.56
     bû
    0.53
     país
    0.53
    எல்
    0.51
    مة
    0.49
    kę
    0.49
     drip
    0.48
     beetroot
    0.48
     sanit
    0.48
    Activations Density 0.016%

    No Known Activations