© 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. 30519
    Prev
    Next
    INDEX
    Explanations

    Russian and other languages

    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
    ят
    0.60
     صدي
    0.56
    os
    0.54
     регу
    0.52
     einge
    0.52
     VEGFR
    0.52
     regulator
    0.51
     managed
    0.51
     regi
    0.50
    н
    0.50
    POSITIVE LOGITS
    ຂອງ
    0.54
    作成
    0.50
    скае
    0.50
    ዎ
    0.50
    ফাজ
    0.49
     avril
    0.48
    یاز
    0.48
    WT
    0.48
     skating
    0.48
    ຂໍ
    0.48
    Activations Density 0.000%

    No Known Activations