© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15316
    Prev
    Next
    INDEX
    Explanations

    units of measurement, weight, or size

    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_13_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
    Along
    0.51
    A
    0.51
    /**
    0.51
    |
    0.50
    where
    0.49
    to
    0.49
    Over
    0.48
    Findings
    0.48
    Og
    0.48
    O
    0.48
    POSITIVE LOGITS
     îm
    0.63
    漪
    0.59
     පේශ
    0.59
     prést
    0.59
     große
    0.58
     галакти
    0.55
    đu
    0.55
     活動
    0.55
     tâ
    0.55
     ál
    0.54
    Activations Density 0.054%

    No Known Activations