© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177507
    Prev
    Next
    INDEX
    Explanations

    religious texts and divine presence

    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_29_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
     行
    0.42
    行
    0.40
     pasaj
    0.34
    ད་
    0.34
    зах
    0.34
     Myerson
    0.34
    友
    0.34
    裄
    0.33
     hanging
    0.33
    waite
    0.33
    POSITIVE LOGITS
    Algo
    0.43
     amber
    0.41
    Amb
    0.39
     molyb
    0.39
    <unused10>
    0.38
    InitStruct
    0.38
    Tos
    0.37
     fn
    0.37
     ና
    0.37
     formate
    0.36
    Activations Density 0.002%

    No Known Activations