© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232166
    Prev
    Next
    INDEX
    Explanations

    numbers following headings

    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_32_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
     చేసుకోవ
    0.35
     విషయంలో
    0.34
     Cout
    0.34
    持つ
    0.33
     እንዲሁ
    0.32
    𐰢
    0.32
    SDL
    0.32
     SIGNAL
    0.32
    Sco
    0.32
    ulina
    0.32
    POSITIVE LOGITS
    ነ
    0.38
     vén
    0.36
     Eric
    0.35
     vena
    0.34
     alg
    0.33
     Hamburg
    0.33
    Baby
    0.33
     Dw
    0.32
    ্লেখ
    0.32
    ഷ്‌
    0.32
    Activations Density 0.004%

    No Known Activations