© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206269
    Prev
    Next
    INDEX
    Explanations

    Bayes' Theorem

    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_19_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
    IGNED
    0.49
     Boundaries
    0.48
     О
    0.41
     Pick
    0.41
     boundaries
    0.41
    住宅
    0.40
     cause
    0.40
     कारण
    0.40
    anej
    0.39
     |”
    0.39
    POSITIVE LOGITS
     മുതല്‍
    0.53
     Technologien
    0.51
    眅
    0.47
     দেবী
    0.46
     வளர்ச்ச
    0.45
    rath
    0.45
     technologies
    0.44
    iori
    0.43
    prism
    0.43
     దేవ
    0.43
    Activations Density 0.003%

    No Known Activations