© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1011
    Prev
    Next
    INDEX
    Explanations

    screen size inches

    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_39_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
    вица
    0.39
     гром
    0.39
    Commissioner
    0.38
     విశ్వ
    0.37
    Duck
    0.36
     قو
    0.35
    itteln
    0.35
    >(_
    0.35
     liefern
    0.35
     deliverables
    0.34
    POSITIVE LOGITS
     inch
    1.19
     Inch
    1.13
    inch
    1.06
    インチ
    1.02
     inches
    0.98
    Inch
    0.98
     pouces
    0.95
     Inches
    0.93
    寸
    0.91
    inches
    0.89
    Activations Density 0.048%

    No Known Activations