© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33345
    Prev
    Next
    INDEX
    Explanations

    uric acid crystals, levels

    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_3_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
    는
    0.82
    是
    0.81
    是很
    0.69
     Przed
    0.68
     Chaque
    0.68
    是被
    0.68
     Bibliothèque
    0.66
    是他
    0.66
    로
    0.64
    ან
    0.64
    POSITIVE LOGITS
    a
    0.84
    1
    0.82
    f
    0.80
    s
    0.76
    t
    0.73
    sl
    0.71
    sing
    0.71
    ias
    0.70
     sums
    0.68
    c
    0.68
    Activations Density 0.001%

    No Known Activations