© 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. 206850
    Prev
    Next
    INDEX
    Explanations

    Levy

    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
    ۔
    0.72
     час
    0.64
    бычно
    0.63
    ви
    0.63
    는
    0.63
    ።
    0.61
    は
    0.61
    gunakan
    0.59
    ве
    0.57
    canal
    0.57
    POSITIVE LOGITS
     O
    0.78
    ID
    0.77
    ih
    0.76
    O
    0.76
    IS
    0.75
    ’
    0.75
    f
    0.73
     that
    0.71
    it
    0.70
    EL
    0.70
    Activations Density 0.000%

    No Known Activations