© 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. 47098
    Prev
    Next
    INDEX
    Explanations

    lot of

    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
    χυ
    0.54
    NonUser
    0.50
    şiv
    0.50
     செய்வத
    0.50
     Wszyst
    0.50
     TÜ
    0.49
     totalité
    0.49
     تناول
    0.48
     Биз
    0.48
     Р
    0.47
    POSITIVE LOGITS
    वर्ती
    0.54
     가지
    0.52
    ailing
    0.51
     Stirling
    0.50
    esas
    0.50
     tradición
    0.49
     venden
    0.49
    essing
    0.49
     grime
    0.48
    ame
    0.48
    Activations Density 0.023%

    No Known Activations