© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233061
    Prev
    Next
    INDEX
    Explanations

    unwound

    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_6_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
    며
    1.05
     I
    1.00
    ли
    0.95
    적인
    0.95
    монт
    0.94
     Yarm
    0.92
     médiocrement
    0.89
    類の
    0.89
    <unused1004>
    0.89
    ών
    0.89
    POSITIVE LOGITS
    {
    1.35
    _
    1.20
    ス
    1.13
    ه
    1.07
    س
    1.05
    '
    1.05
    ۲
    1.00
    ה
    0.99
     up
    0.97
    da
    0.97
    Activations Density 0.000%

    No Known Activations