© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179906
    Prev
    Next
    INDEX
    Explanations

    Sk

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    kamp
    0.44
     Calvin
    0.40
     Kalimantan
    0.39
     Katherine
    0.38
     eth
    0.38
    菂
    0.37
     Upp
    0.36
     Kaleidoscope
    0.36
    munder
    0.36
    营
    0.36
    POSITIVE LOGITS
    চীন
    0.48
     pacc
    0.42
    acchati
    0.40
    ufficient
    0.40
    abbati
    0.38
    SCHEMA
    0.38
    حة
    0.38
     ताज
    0.38
    ULATORY
    0.38
    awara
    0.37
    Activations Density 0.000%

    No Known Activations