© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19681
    Prev
    Next
    INDEX
    Explanations

    gates

    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_15_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
    /
    0.51
     analisis
    0.50
     analyses
    0.47
     dvara
    0.47
     marathon
    0.46
     conclusion
    0.46
     analysis
    0.46
     saada
    0.45
    =
    0.45
     regimen
    0.45
    POSITIVE LOGITS
     जैसे
    0.61
     Car
    0.60
     Apl
    0.60
     Heron
    0.57
     Уен
    0.57
    fragt
    0.56
     चिंग
    0.55
     Trad
    0.54
    𝓂
    0.54
     Фран
    0.54
    Activations Density 0.001%

    No Known Activations