© 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. 211993
    Prev
    Next
    INDEX
    Explanations

    cities and airports

    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
     auxiliar
    0.46
    Вакан
    0.44
    hoot
    0.42
     Qualquer
    0.42
     Cualquier
    0.42
     Auxiliary
    0.41
     śmier
    0.41
     Waterfront
    0.41
     Painters
    0.40
    ╁
    0.40
    POSITIVE LOGITS
     नमक
    0.39
     napp
    0.39
    ALOG
    0.39
     బ్లా
    0.39
     ruby
    0.38
    മി
    0.38
     office
    0.38
    estic
    0.38
     oz
    0.38
     flip
    0.38
    Activations Density 0.001%

    No Known Activations