© 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. 135328
    Prev
    Next
    INDEX
    Explanations

    density, weight, and ratio

    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
    Not in Any Lists

    No Comments

    Negative Logits
    I
    1.10
    2
    1.10
    K
    1.01
     to
    0.97
    ll
    0.88
    9
    0.88
    6
    0.86
    U
    0.85
    8
    0.85
    ↵↵
    0.84
    POSITIVE LOGITS
    ри
    1.13
    ного
    1.07
    يرا
    0.91
    ем
    0.86
    ни
    0.85
    ных
    0.83
    ные
    0.82
    ной
    0.82
    т
    0.80
    ور
    0.80
    Activations Density 0.009%

    No Known Activations