© 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. 217669
    Prev
    Next
    INDEX
    Explanations

    Pancha 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
     Goes
    0.45
    امية
    0.43
    امی
    0.42
     relic
    0.41
    豫
    0.41
     అమ
    0.41
    امي
    0.40
     imidazole
    0.39
    ابس
    0.39
    ப்பழ
    0.39
    POSITIVE LOGITS
     দক্ষতা
    0.40
    邱
    0.37
    Stroke
    0.37
     stroke
    0.36
    кту
    0.36
    Quantitative
    0.36
     hect
    0.36
     ched
    0.35
     cuantit
    0.34
    羌
    0.34
    Activations Density 0.000%

    No Known Activations