© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121119
    Prev
    Next
    INDEX
    Explanations

    questions about AI beliefs

    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_37_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
    das
    0.37
     маслом
    0.36
    ழிப்பு
    0.35
    urato
    0.34
    SA
    0.34
    cas
    0.34
    SIL
    0.33
    Dü
    0.32
    複
    0.32
    file
    0.32
    POSITIVE LOGITS
     of
    1.13
     của
    1.04
     Of
    1.04
    Of
    1.02
    ของ
    1.00
     của
    0.97
    of
    0.96
     של
    0.96
    ຂອງ
    0.95
     ofthe
    0.89
    Activations Density 0.090%

    No Known Activations