© 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. 247299
    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
    Not in Any Lists

    No Comments

    Negative Logits
     clicking
    0.42
     klicken
    0.41
     clicks
    0.41
    바이
    0.38
    
    0.37
     tro
    0.37
     click
    0.36
     Appe
    0.36
     taken
    0.36
     integral
    0.36
    POSITIVE LOGITS
    対称
    0.46
     সবুজ
    0.39
    .??
    0.39
    丵
    0.39
     sementara
    0.38
    rawdę
    0.38
     ተመሳሳይ
    0.38
    推薦
    0.37
     !}\
    0.36
     Warna
    0.36
    Activations Density 0.000%

    No Known Activations