© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65081
    Prev
    Next
    INDEX
    Explanations

    So

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    romechanical
    0.41
    ową
    0.38
    weaving
    0.38
     ’’
    0.38
    ˝
    0.38
     '''
    0.36
    oku
    0.35
     /\
    0.35
     ?>"
    0.35
     ′
    0.35
    POSITIVE LOGITS
    рик
    0.40
     mura
    0.38
     Cast
    0.38
     Ll
    0.38
    лли
    0.38
    лла
    0.37
     Lara
    0.37
     Rada
    0.37
     паци
    0.36
     Rish
    0.36
    Activations Density 0.004%

    No Known Activations