© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257265
    Prev
    Next
    INDEX
    Explanations

    where applicable/relevant/possible

    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_22_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
    鍊
    0.48
    Chois
    0.46
    㳻
    0.46
    㽡
    0.46
    传染
    0.45
    共产
    0.44
    𒈪
    0.44
     Лі
    0.43
    يلي
    0.43
    閫
    0.43
    POSITIVE LOGITS
     Pacquiao
    0.48
     dreamstime
    0.48
     ceasefire
    0.48
     March
    0.47
     gearing
    0.45
    c
    0.44
    ất
    0.43
    ONO
    0.43
    Aslamualaikum
    0.42
    deployment
    0.42
    Activations Density 0.000%

    No Known Activations