© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212901
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    нє
    0.41
    ﱢ
    0.41
    ّا
    0.41
     Jeju
    0.40
     Nave
    0.40
     Establishment
    0.39
    ərd
    0.39
    ّى
    0.38
     ester
    0.38
    jedno
    0.38
    POSITIVE LOGITS
    aus
    0.39
    aer
    0.38
    ®
    0.37
    ngths
    0.35
    zeichen
    0.35
    getHours
    0.35
    つけた
    0.34
    �
    0.34
    animate
    0.34
    },{"
    0.34
    Activations Density 0.000%

    No Known Activations