© 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. 221131
    Prev
    Next
    INDEX
    Explanations

    bible verses and explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    あたり
    0.43
     изо
    0.41
    Reli
    0.39
    РСР
    0.38
    ﮕ
    0.38
    縞
    0.37
    изо
    0.37
    ▬
    0.37
     Rhône
    0.36
     plumbing
    0.35
    POSITIVE LOGITS
     작품
    0.37
    inued
    0.37
     mar
    0.36
     inactivation
    0.36
     Median
    0.36
     不能
    0.35
     median
    0.35
    ([
    0.35
    യുടെ
    0.34
     getir
    0.34
    Activations Density 0.000%

    No Known Activations