© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40656
    Prev
    Next
    INDEX
    Explanations

    T-cell activation, proliferation, development

    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_3_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
    ۰
    0.64
     різні
    0.63
    们
    0.61
    ور
    0.60
    نيه
    0.59
    手表
    0.59
    \{
    0.58
    ното
    0.58
    дент
    0.58
     információ
    0.58
    POSITIVE LOGITS
    ش
    0.85
    re
    0.82
    น
    0.73
    sk
    0.71
    rt
    0.69
    n
    0.68
    Sp
    0.67
    ку
    0.64
    se
    0.63
    the
    0.63
    Activations Density 0.002%

    No Known Activations