© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116318
    Prev
    Next
    INDEX
    Explanations

    quantities and comparisons

    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_38_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
    媢
    0.43
    Expressions
    0.38
    榆
    0.38
    ান্দ
    0.38
    Nay
    0.38
     දි
    0.38
    娓
    0.36
     अल्ट्रा
    0.35
    
    0.35
     आफ्टरनून
    0.35
    POSITIVE LOGITS
     ounces
    0.91
     grams
    0.88
     kilometres
    0.87
     kilograms
    0.87
     kilometers
    0.86
     milligrams
    0.85
     centimeters
    0.84
     gramos
    0.84
     watts
    0.83
     kilos
    0.82
    Activations Density 0.220%

    No Known Activations