© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248099
    Prev
    Next
    INDEX
    Explanations

    blood circulation

    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_56_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
     sang
    2.73
    Sang
    2.42
     Sang
    2.39
    sang
    2.22
     Sangh
    1.19
     संग
    0.99
    桑
    0.97
     संगम
    0.91
     sings
    0.89
     shot
    0.84
    POSITIVE LOGITS
     vul
    0.39
     vulcan
    0.38
     መል
    0.38
     सूचित
    0.37
     S
    0.36
     જવાબ
    0.36
    шеб
    0.36
    (({
    0.35
    wells
    0.35
     pasting
    0.35
    Activations Density 0.001%

    No Known Activations