© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41141
    Prev
    Next
    INDEX
    Explanations

    recording

    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_11_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
     vidéos
    0.36
     영상
    0.32
     ویڈیو
    0.30
     ভিডিও
    0.29
     الفيديو
    0.28
     겨
    0.28
     filmm
    0.27
     katva
    0.27
     유튜브
    0.27
     vídeos
    0.27
    POSITIVE LOGITS
    us
    0.32
    is
    0.32
    ال
    0.31
    AR
    0.30
    ல்
    0.30
     идет
    0.29
    ઓ
    0.29
     !",
    0.28
    ar
    0.28
    اس
    0.28
    Activations Density 0.004%

    No Known Activations