© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8714
    Prev
    Next
    INDEX
    Explanations

    off-roading

    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_13_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
    iftung
    0.54
    itochond
    0.52
    efficients
    0.49
     食品
    0.49
     Хоккей
    0.49
    㿝
    0.49
     rendement
    0.48
     Lancet
    0.48
    jści
    0.48
    䡓
    0.47
    POSITIVE LOGITS
     Walton
    0.55
     recreational
    0.50
     difficol
    0.50
    Notice
    0.48
     accesible
    0.48
     you
    0.48
    Compose
    0.48
     roam
    0.47
     restricciones
    0.47
    Park
    0.47
    Activations Density 0.004%

    No Known Activations