© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209631
    Prev
    Next
    INDEX
    Explanations

    cornerstone of

    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_5_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
    ai
    1.13
    l
    0.90
    ).
    0.85
     an
    0.82
     détermine
    0.82
     la
    0.81
     preclude
    0.80
     prepare
    0.80
     deny
    0.80
     broaden
    0.78
    POSITIVE LOGITS
    ions
    0.95
    е
    0.95
    1
    0.92
    은
    0.91
    ą
    0.90
    т
    0.88
    ut
    0.87
    ę
    0.86
    ul
    0.83
    вых
    0.82
    Activations Density 0.002%

    No Known Activations