© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135232
    Prev
    Next
    INDEX
    Explanations

    shin splints prevention

    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_1_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
    0
    1.84
    of
    1.54
    s
    1.34
    ون
    1.30
    ۰
    1.29
    ur
    1.28
    de
    1.17
    ד
    1.16
    д
    1.14
    ע
    1.13
    POSITIVE LOGITS
    ."))
    1.09
     procl
    1.09
    u
    1.08
    țit
    0.99
     certific
    0.96
    
    0.94
    kere
    0.93
    ٤
    0.93
     kefir
    0.91
     fintech
    0.90
    Activations Density 0.000%

    No Known Activations