© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206590
    Prev
    Next
    INDEX
    Explanations

    somatic cell nuclear transfer

    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_37_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
     illiterate
    0.42
     بط
    0.41
    icket
    0.40
     आदिवासी
    0.38
    abad
    0.38
    horizontalLayout
    0.38
    鳎
    0.37
     இல
    0.36
    タイル
    0.36
     Bildern
    0.36
    POSITIVE LOGITS
     Clone
    0.70
     cloning
    0.69
     Cloning
    0.66
    Clone
    0.66
     clone
    0.65
     cloned
    0.65
     clones
    0.63
    clone
    0.60
     clon
    0.57
     clonal
    0.49
    Activations Density 0.001%

    No Known Activations