© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93930
    Prev
    Next
    INDEX
    Explanations

    propose/introduce

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    一个新的
    0.50
    [&
    0.50
     নতুন
    0.47
     الجديد
    0.44
     utilizza
    0.44
     новий
    0.44
     nowych
    0.44
     новых
    0.43
     nuovi
    0.43
     new
    0.42
    POSITIVE LOGITS
     and
    0.55
     End
    0.47
     end
    0.46
     \
    0.46
     such
    0.43
     Such
    0.42
    such
    0.41
    End
    0.41
     END
    0.39
     substantial
    0.37
    Activations Density 0.001%

    No Known Activations