© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205562
    Prev
    Next
    INDEX
    Explanations

    in or with certain words

    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_20_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
     Ο
    0.46
    薹
    0.45
    劏
    0.44
     RasterModelGrid
    0.44
     sphing
    0.44
     achievable
    0.43
    São
    0.43
     హిట్
    0.43
     fondée
    0.43
     underwriting
    0.43
    POSITIVE LOGITS
     Floyd
    0.47
    we
    0.44
     Martha
    0.44
     ,
    0.44
    我们就
    0.44
    ung
    0.41
     Beast
    0.41
    roon
    0.41
    way
    0.41
    la
    0.40
    Activations Density 0.009%

    No Known Activations