© 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. 48352
    Prev
    Next
    INDEX
    Explanations

    code/punctuation/separators

    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_31_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
     প্রবন্ধ
    0.39
    まれ
    0.37
     先
    0.34
    યુ
    0.33
     contraceptive
    0.33
     fauve
    0.33
     প্রাচ
    0.33
    비를
    0.32
     трубы
    0.31
     статистика
    0.31
    POSITIVE LOGITS
    }^{+}$
    0.35
    uty
    0.34
    ‌هایی
    0.33
     secre
    0.32
     another
    0.31
     “[
    0.31
    িতেছে
    0.31
    ="//
    0.31
     Galileo
    0.30
    maja
    0.30
    Activations Density 0.000%

    No Known Activations