© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18918
    Prev
    Next
    INDEX
    Explanations

    government bodies and statistics

    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_34_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
    hip
    0.40
    ཛ
    0.37
    ambuf
    0.37
    кульп
    0.34
     gratu
    0.34
     drumming
    0.34
     predator
    0.34
    anek
    0.34
    일상
    0.34
    ሑ
    0.34
    POSITIVE LOGITS
     एजेंसी
    0.44
     কমিশন
    0.43
     commission
    0.40
     Liye
    0.40
     Bure
    0.39
    وغ
    0.39
     एजेंसियों
    0.39
    QUESTION
    0.38
    commission
    0.38
    hattis
    0.38
    Activations Density 0.005%

    No Known Activations