© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193427
    Prev
    Next
    INDEX
    Explanations

    typesetting, LaTeX, documents

    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_9_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
    ين
    1.43
    ش
    0.99
    नगर
    0.98
    ون
    0.95
    inFile
    0.91
    nés
    0.89
    ంలో
    0.88
    ंसारी
    0.88
    ={\
    0.86
    િ
    0.85
    POSITIVE LOGITS
     device
    0.90
     (
    0.73
    ,
    0.71
     expectancy
    0.68
     workpiece
    0.68
     warning
    0.67
     locomotion
    0.67
     perangkat
    0.67
     bidirectional
    0.66
     vehicle
    0.65
    Activations Density 0.000%

    No Known Activations