© 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. 47096
    Prev
    Next
    INDEX
    Explanations

    alternatives or conditional conjunctions

    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
    瘙
    0.68
    ａ
    0.57
    ка
    0.57
    basename
    0.57
    a
    0.56
    κ
    0.56
    uad
    0.55
     hinders
    0.55
    ם
    0.55
    ω
    0.55
    POSITIVE LOGITS
     сложных
    0.58
     clay
    0.52
    es
    0.51
     विदेशों
    0.50
    िशन
    0.50
    ONES
    0.50
     система
    0.48
     автомоби
    0.47
    餃
    0.47
     таки
    0.45
    Activations Density 0.004%

    No Known Activations