© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67609
    Prev
    Next
    INDEX
    Explanations

    N.K. Jemisin

    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_41_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
    里克
    0.42
    .$(
    0.37
     cartridges
    0.37
     cartridge
    0.37
    שות
    0.36
    ückt
    0.35
     ویک
    0.35
    шни
    0.35
    стов
    0.34
     Nationality
    0.34
    POSITIVE LOGITS
    ateau
    0.37
    COMPAR
    0.37
    合理的
    0.36
    faa
    0.36
     ٣
    0.36
    Compar
    0.36
    ajem
    0.35
    게임
    0.35
    èbre
    0.35
    UNLOCK
    0.35
    Activations Density 0.002%

    No Known Activations