© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35232
    Prev
    Next
    INDEX
    Explanations

    support system figures

    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_11_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
    czka
    0.60
    anns
    0.59
    ட்கள்
    0.59
     المُ
    0.57
     ['(?
    0.55
     днем
    0.55
    ïne
    0.53
    нгтон
    0.53
     gegründet
    0.52
    adai
    0.52
    POSITIVE LOGITS
     $
    0.71
     minute
    0.68
     teacher
    0.63
    0.62
     the
    0.56
     machine
    0.55
     typing
    0.54
     G
    0.53
     bureaucratic
    0.53
     precum
    0.52
    Activations Density 0.059%

    No Known Activations