© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83943
    Prev
    Next
    INDEX
    Explanations

    multi- prefix, Northern, Thermo, Embedded, H, L, Profit, Scale, Python

    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_29_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
     habit
    0.35
     plagued
    0.33
     stormy
    0.33
     trilogy
    0.32
     ’
    0.31
     ∗
    0.31
     __
    0.31
     "*.
    0.31
     strom
    0.30
     choreographer
    0.30
    POSITIVE LOGITS
    лы
    0.31
    лина
    0.31
    ridge
    0.31
    ifferentiate
    0.31
    lay
    0.31
    methylation
    0.30
    ropy
    0.29
    startY
    0.29
    lash
    0.29
    মন্দ
    0.29
    Activations Density 0.026%

    No Known Activations