© 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. 51744
    Prev
    Next
    INDEX
    Explanations

    hexagon/hexagonal

    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
    -
    0.62
    ad
    0.60
    .
    0.59
    (
    0.59
    et
    0.57
    re
    0.56
    to
    0.54
    '
    0.52
    n
    0.52
    or
    0.51
    POSITIVE LOGITS
    いた
    0.63
    鄭
    0.61
    ťa
    0.59
    зге
    0.57
    ఇ
    0.57
     झाले
    0.54
     Vì
    0.54
     Học
    0.53
    ಓ
    0.53
    ]}/
    0.52
    Activations Density 0.000%

    No Known Activations