© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177343
    Prev
    Next
    INDEX
    Explanations

    version numbers and dependency specifications

    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_29_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
    変数
    0.44
     привіт
    0.42
     посредством
    0.41
     बायोलॉजी
    0.40
     hipótesis
    0.39
     ማድረግ
    0.39
     অপ্রত্যাশিত
    0.39
    仨
    0.38
    ิติ
    0.38
     አስ
    0.38
    POSITIVE LOGITS
     singapore
    0.37
     employer
    0.37
     cleaner
    0.36
    လေ
    0.36
     citizens
    0.35
    來源
    0.34
    omized
    0.34
     pistachio
    0.34
     конку
    0.34
     munc
    0.34
    Activations Density 0.002%

    No Known Activations