© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51849
    Prev
    Next
    INDEX
    Explanations

    sg, SGM, sgml, sgplot, sgRNA

    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_10_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
    ای
    1.12
    َی
    0.88
    の
    0.82
    الی
    0.80
     tačiau
    0.80
    ِی
    0.78
     lapses
    0.78
     حسین
    0.77
    ‌ی
    0.77
    え
    0.77
    POSITIVE LOGITS
    the
    1.01
    is
    0.93
    。
    0.88
    ного
    0.86
    yn
    0.80
    sthe
    0.73
    ure
    0.72
    does
    0.72
    orie
    0.71
    ideen
    0.70
    Activations Density 0.000%

    No Known Activations