© 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. 134264
    Prev
    Next
    INDEX
    Explanations

    twists

    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
    ناک
    0.43
    Sandra
    0.40
    ska
    0.40
    (!$
    0.39
    Frank
    0.38
     Frank
    0.38
    вані
    0.38
    int
    0.38
    wać
    0.38
     satan
    0.38
    POSITIVE LOGITS
    ಯ್
    0.42
     पर्यंत
    0.39
     પડી
    0.39
     VL
    0.39
     ँ
    0.38
     architect
    0.37
     Fertility
    0.37
    遊
    0.37
     गांधी
    0.36
    ኞች
    0.36
    Activations Density 0.000%

    No Known Activations