© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41293
    Prev
    Next
    INDEX
    Explanations

    让 [someone] [do something]

    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_11_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
     cambia
    0.62
     kā
    0.56
     вони
    0.55
    Կ
    0.54
    äß
    0.54
     انہوں
    0.53
    ภัณฑ์
    0.52
     kanilang
    0.52
     họ
    0.52
     трябва
    0.51
    POSITIVE LOGITS
    in
    0.66
    el
    0.63
    or
    0.62
    л
    0.61
    z
    0.61
    tonne
    0.59
    le
    0.57
     $\
    0.57
    é
    0.57
    жон
    0.56
    Activations Density 0.000%

    No Known Activations