© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200198
    Prev
    Next
    INDEX
    Explanations

    tankards

    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_6_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
    ↵
    0.83
     मास
    0.63
    actoring
    0.56
    gruppe
    0.54
    .
    0.54
    る
    0.52
    iveness
    0.51
    ib
    0.50
    aaaa
    0.49
    ges
    0.48
    POSITIVE LOGITS
     for
    0.89
     It
    0.86
     to
    0.75
    н
    0.71
     and
    0.64
    <0x0D>
    0.63
    0
    0.61
    ó
    0.60
     from
    0.59
     was
    0.58
    Activations Density 0.000%

    No Known Activations