© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    your Lie in April

    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_39_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
    ivided
    0.37
    麩
    0.37
    ⤴
    0.37
     ten
    0.36
    Контак
    0.33
     zuf
    0.33
    льбе
    0.33
     fourteen
    0.32
     INTE
    0.32
    BibitemOpen
    0.32
    POSITIVE LOGITS
    deformation
    0.37
     scoot
    0.37
    /');
    0.36
     ensembles
    0.36
     determinada
    0.36
     deformations
    0.35
     physicist
    0.35
     Sp
    0.34
    asas
    0.34
     कायदा
    0.33
    Activations Density 0.000%

    No Known Activations