© 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. 33637
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     closure
    1.09
     закры
    1.02
    Closure
    1.01
    关闭
    0.98
     Closure
    0.98
    閉
    0.98
     Closing
    0.96
     closing
    0.96
     关闭
    0.96
    闭
    0.95
    POSITIVE LOGITS
     Ros
    0.42
     ros
    0.39
    imientos
    0.39
     instincts
    0.38
    ButtonClick
    0.38
     Santana
    0.37
    Ros
    0.37
     Varn
    0.37
     Garnier
    0.37
     calling
    0.36
    Activations Density 0.018%

    No Known Activations