© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2149
    Prev
    Next
    INDEX
    Explanations

    growth and access themes

    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_40_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
     mmf
    0.38
     এগিয়ে
    0.37
     hurdles
    0.36
    Bindings
    0.36
    回顾
    0.36
    женного
    0.36
     Dorn
    0.35
    женные
    0.35
    ả
    0.34
    推進
    0.34
    POSITIVE LOGITS
     themes
    0.52
     Tema
    0.52
    Theme
    0.50
     Theme
    0.50
    Themes
    0.49
     Themes
    0.47
     theme
    0.47
    theme
    0.45
    access
    0.45
     accès
    0.44
    Activations Density 0.093%

    No Known Activations