© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74470
    Prev
    Next
    INDEX
    Explanations

    weights, matrix, embedding, system

    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_31_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
     போய்
    0.37
     Paper
    0.35
     Oil
    0.35
    <0x9A>
    0.34
    ارهای
    0.34
     Weiner
    0.34
     Hyd
    0.34
     preferencias
    0.34
     Herc
    0.34
     부정
    0.34
    POSITIVE LOGITS
    ោ
    0.40
    boldsymbol
    0.34
    တီ
    0.34
    бору
    0.34
    вань
    0.33
    စ္စည်း
    0.33
    cion
    0.33
    undered
    0.33
     كري
    0.33
    hourly
    0.32
    Activations Density 0.000%

    No Known Activations