© 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. 37217
    Prev
    Next
    INDEX
    Explanations

    Russian words

    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
    Bay
    0.42
    던
    0.40
    Ti
    0.38
    Im
    0.38
    Collabor
    0.37
    Pen
    0.37
    rera
    0.37
     Pinnacle
    0.37
     Mein
    0.36
     الدوال
    0.36
    POSITIVE LOGITS
     மணி
    0.43
    assing
    0.39
    啻
    0.39
    மணி
    0.38
     গিয়ে
    0.36
    hend
    0.36
     heirs
    0.36
     loci
    0.36
    ாச
    0.35
     बल्कि
    0.35
    Activations Density 0.001%

    No Known Activations