© 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. 15271
    Prev
    Next
    INDEX
    Explanations

    stylesheet links

    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
    ၆
    0.52
     sna
    0.51
    赋予
    0.51
    capitalize
    0.50
    “(
    0.50
     baixo
    0.49
     bajo
    0.49
     pena
    0.49
    وانی
    0.49
    "<<
    0.48
    POSITIVE LOGITS
    jahtera
    0.52
    ి
    0.50
     competing
    0.46
    ลล์
    0.46
     Sta
    0.45
    ř
    0.45
    rizione
    0.44
     A
    0.44
     '~
    0.44
    URA
    0.43
    Activations Density 0.001%

    No Known Activations