© 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. 7672
    Prev
    Next
    INDEX
    Explanations

    physical reactions

    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
     ব্রি
    0.39
     wheat
    0.38
    reciate
    0.38
     égal
    0.38
     orij
    0.38
     sesize
    0.37
     ciné
    0.37
    訛
    0.37
    儼
    0.36
     surm
    0.36
    POSITIVE LOGITS
     fastening
    0.39
    antal
    0.39
    wiring
    0.38
     smiles
    0.38
     harder
    0.37
    iances
    0.37
    Straight
    0.36
    Mechanical
    0.36
     SF
    0.36
     Nucle
    0.36
    Activations Density 0.101%

    No Known Activations