© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151790
    Prev
    Next
    INDEX
    Explanations

    current-carrying wire

    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_18_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
     있
    0.46
     chá
    0.46
     suka
    0.45
    ด์
    0.45
     Polaribacter
    0.45
     kop
    0.45
     parsed
    0.44
     acumen
    0.43
    щ
    0.43
     faktor
    0.43
    POSITIVE LOGITS
    mrow
    0.45
    ショッピング
    0.44
    upp
    0.44
    projectlombok
    0.44
    罡
    0.43
    mi
    0.43
    pi
    0.43
    ‌آ
    0.43
    crystall
    0.43
    sted
    0.43
    Activations Density 0.000%

    No Known Activations