© 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. 8782
    Prev
    Next
    INDEX
    Explanations

    as X as Y

    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
    ratulations
    0.48
     მხოლოდ
    0.48
     consolation
    0.48
    𝘈
    0.47
     contribution
    0.46
     pleading
    0.46
    estic
    0.46
    लिड
    0.46
    ˑ
    0.45
    ORDAN
    0.45
    POSITIVE LOGITS
    t
    0.52
    n
    0.49
    이에
    0.47
    트는
    0.47
     башка
    0.47
    ز
    0.46
     Marte
    0.46
    普通
    0.44
    트에
    0.44
    트
    0.44
    Activations Density 0.013%

    No Known Activations