© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193776
    Prev
    Next
    INDEX
    Explanations

    Evangelion and audit

    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_15_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
    บ
    0.50
     یاد
    0.47
    📱
    0.47
     encoding
    0.47
    ب
    0.46
    ่อ
    0.45
     fainting
    0.44
    भाई
    0.43
     smartphone
    0.43
    <0x93>
    0.43
    POSITIVE LOGITS
     Nazi
    0.55
    čkom
    0.55
    öra
    0.54
    ulares
    0.54
     lecithin
    0.54
    kve
    0.54
    秝
    0.54
    綑
    0.54
    OCI
    0.53
     zeml
    0.52
    Activations Density 0.003%

    No Known Activations