© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161322
    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_31_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
     rehab
    0.40
    ebilirsiniz
    0.40
     sidel
    0.40
     стимули
    0.40
     Vip
    0.39
     গ্রামে
    0.37
     ../
    0.37
     stim
    0.37
     stimulating
    0.36
    ვით
    0.36
    POSITIVE LOGITS
    执行
    0.40
     आक
    0.37
     생
    0.36
    FBSDKApp
    0.35
    Trivia
    0.35
     ٹھ
    0.35
     तला
    0.35
    Upp
    0.34
     గొప్ప
    0.34
     Exec
    0.34
    Activations Density 0.000%

    No Known Activations