© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226955
    Prev
    Next
    INDEX
    Explanations

    programmatic solve CAPTCHAs

    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_10_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
    '
    0.47
     가지
    0.45
     роди
    0.44
     tous
    0.43
    으로
    0.43
     deux
    0.41
    ფილი
    0.40
    isin
    0.40
     klart
    0.40
     Felipe
    0.40
    POSITIVE LOGITS
    ैया
    0.59
    滀
    0.59
    keye
    0.50
    discussion
    0.49
    Datab
    0.47
     Frage
    0.46
     Coaching
    0.46
    DICTION
    0.46
    Purg
    0.46
    乩
    0.46
    Activations Density 0.000%

    No Known Activations