© 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. 121529
    Prev
    Next
    INDEX
    Explanations

    mortality rate

    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
     می‌باشد
    0.64
     وړاندوینه
    0.57
     don
    0.56
     aren
    0.55
     pampered
    0.52
     wasn
    0.52
     doesn
    0.50
     disreg
    0.50
    𝘞
    0.50
     dõi
    0.50
    POSITIVE LOGITS
    Traité
    0.68
    ir
    0.67
    ش
    0.66
     Côte
    0.64
    kova
    0.63
    //
    0.62
    ка
    0.62
    rischen
    0.62
    2
    0.62
    an
    0.61
    Activations Density 0.000%

    No Known Activations