© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102908
    Prev
    Next
    INDEX
    Explanations

    hospitals and healthcare organizations

    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_14_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
    Kah
    0.57
    Few
    0.55
    impossible
    0.55
    University
    0.53
    anyag
    0.51
    le
    0.51
    gh
    0.51
    transfer
    0.51
    ˗
    0.50
    Transfer
    0.50
    POSITIVE LOGITS
     wła
    0.54
    <unused1877>
    0.54
    と呼ば
    0.51
     жүкт
    0.50
     или
    0.50
    літ
    0.49
     labeled
    0.49
    のア
    0.48
    キット
    0.48
     autom
    0.47
    Activations Density 0.000%

    No Known Activations