© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200110
    Prev
    Next
    INDEX
    Explanations

    zend framework

    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_37_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
     автоном
    0.40
     nodeId
    0.40
    器
    0.38
    口
    0.38
    िंग
    0.37
    valve
    0.37
     pleading
    0.37
    romyalgia
    0.37
     Personalized
    0.36
     разбира
    0.35
    POSITIVE LOGITS
     processions
    0.40
    ziak
    0.40
    genes
    0.39
     onderdeel
    0.38
     marches
    0.38
     koost
    0.37
    쿡
    0.37
     NEXT
    0.37
     Pisa
    0.37
    meson
    0.35
    Activations Density 0.000%

    No Known Activations