© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62460
    Prev
    Next
    INDEX
    Explanations

    documentation guides

    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_11_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
    챕
    0.49
     bahut
    0.47
    章
    0.47
     তদন্ত
    0.46
     système
    0.45
     curviliné
    0.45
     Système
    0.45
     ਜਾਂ
    0.44
     chapitre
    0.44
    šten
    0.44
    POSITIVE LOGITS
    愘
    0.49
     margarita
    0.46
     freshwater
    0.46
     morphism
    0.45
     প্রত্যাবর্তন
    0.44
     अन्दर
    0.44
    VAL
    0.43
    寄せ
    0.43
     NG
    0.43
    сад
    0.43
    Activations Density 0.002%

    No Known Activations