© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37116
    Prev
    Next
    INDEX
    Explanations

    bh sound

    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_50_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
     नि
    0.93
     니
    0.88
     Ни
    0.79
     Nib
    0.77
     Nil
    0.76
    Nil
    0.74
     Niv
    0.74
     ní
    0.73
     Ni
    0.72
    Ни
    0.72
    POSITIVE LOGITS
     భ
    0.45
     ભ
    0.45
    Bj
    0.43
     bh
    0.43
     bj
    0.43
     bhaj
    0.43
     бю
    0.42
     भ
    0.42
     Bh
    0.41
     Susie
    0.41
    Activations Density 0.004%

    No Known Activations