© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122566
    Prev
    Next
    INDEX
    Explanations

    bladder, urination, or holding pee

    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_38_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
     urinary
    0.61
     Urinary
    0.60
     urin
    0.57
    尿
    0.57
     urine
    0.54
     UTI
    0.54
     моче
    0.50
     Urine
    0.49
     UT
    0.47
     uro
    0.46
    POSITIVE LOGITS
     वायरस
    0.43
     გას
    0.41
    ilaian
    0.41
    မြို့
    0.39
    贼
    0.38
    ുപ
    0.38
    hain
    0.37
     निव
    0.37
    村
    0.36
     Contents
    0.36
    Activations Density 0.012%

    No Known Activations