© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238566
    Prev
    Next
    INDEX
    Explanations

    when subjects act

    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_32_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
     Vương
    0.35
     kür
    0.33
     perempuan
    0.33
     gói
    0.32
    }{|
    0.32
     trông
    0.32
    屽
    0.32
     സ്ത്ര
    0.31
     اجازت
    0.31
    ajima
    0.30
    POSITIVE LOGITS
     GLFW
    0.37
    ασίας
    0.36
    )'=='
    0.35
    豊富
    0.35
    UIL
    0.34
     Trade
    0.34
    然
    0.34
     নহে
    0.33
    に向
    0.33
     CREE
    0.33
    Activations Density 0.004%

    No Known Activations