© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30310
    Prev
    Next
    INDEX
    Explanations

    XML schema stylesheet index

    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_10_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
     can
    0.72
     it
    0.64
     i
    0.60
     calcio
    0.59
    지를
    0.58
    っきり
    0.58
    くなります
    0.58
    闓
    0.58
    ೋಜನ
    0.57
     Kenya
    0.57
    POSITIVE LOGITS
    y
    0.82
    ut
    0.79
    '
    0.77
    s
    0.75
    eren
    0.70
    ari
    0.69
    us
    0.69
    ní
    0.67
    ys
    0.66
    ando
    0.66
    Activations Density 0.000%

    No Known Activations