© 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. 215856
    Prev
    Next
    INDEX
    Explanations

    меняет местами

    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
    u
    1.82
    ر
    1.80
    r
    1.78
    d
    1.63
    h
    1.50
    ز
    1.48
    ل
    1.31
    ្សែ
    1.30
    ků
    1.29
    ри
    1.25
    POSITIVE LOGITS
     are
    1.62
    </h2>
    1.48
    ă
    1.30
    </strong>
    1.24
    ע
    1.18
     but
    1.17
     five
    1.16
    </em>
    1.14
    </span>
    1.13
    '
    1.11
    Activations Density 0.001%

    No Known Activations