© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54609
    Prev
    Next
    INDEX
    Explanations

    people died or perished

    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_31_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
    COU
    0.39
    itura
    0.37
     hinsichtlich
    0.37
     begrij
    0.35
     材料
    0.35
     kalan
    0.35
     Material
    0.34
     taki
    0.34
    睉
    0.34
    なかなか
    0.34
    POSITIVE LOGITS
    adores
    0.39
    NumConst
    0.38
    আগ
    0.38
    Blockchain
    0.38
    $.;
    0.37
     रिजर्व
    0.36
    Steady
    0.36
    নিউ
    0.35
     رہنے
    0.35
    Altitude
    0.35
    Activations Density 0.002%

    No Known Activations