© 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. 145179
    Prev
    Next
    INDEX
    Explanations

    Anti-Defamation League

    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
    rensa
    0.21
    season
    0.19
    ќ
    0.18
    ↵
    0.18
    ierra
    0.18
    izers
    0.18
    =
    0.18
    oka
    0.17
    会の
    0.17
    ئا
    0.17
    POSITIVE LOGITS
    мә
    0.20
     hausse
    0.19
    mlung
    0.19
     सरकारी
    0.19
     ductility
    0.19
     массив
    0.19
    ﻞ
    0.19
     deformable
    0.19
     massaging
    0.18
     स्थिर
    0.18
    Activations Density 0.004%

    No Known Activations