© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101480
    Prev
    Next
    INDEX
    Explanations

    textbooks

    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_44_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
    toISOString
    0.47
    渝
    0.41
    俞
    0.39
    uret
    0.39
     Kenny
    0.39
     Xun
    0.39
     बड़
    0.39
    ële
    0.38
    boxylate
    0.38
    ggplot
    0.38
    POSITIVE LOGITS
     cotton
    0.37
    volence
    0.37
     جر
    0.36
     cosecha
    0.36
     coarse
    0.36
     হচ্ছে
    0.35
    coats
    0.35
    윈
    0.34
    舌
    0.34
     contenuti
    0.34
    Activations Density 0.000%

    No Known Activations