© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206597
    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_37_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
     cláus
    0.42
     clauses
    0.38
     IntelliJ
    0.38
     タイプ
    0.38
    炕
    0.38
    査
    0.37
     aDAO
    0.36
     estatales
    0.36
     फास्ट
    0.36
     bist
    0.36
    POSITIVE LOGITS
    jeff
    0.39
    ىلى
    0.39
    Hammer
    0.38
    туры
    0.38
    oten
    0.38
     greasy
    0.38
    Buongiorno
    0.38
    phone
    0.37
    相
    0.37
    usr
    0.37
    Activations Density 0.000%

    No Known Activations