© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209510
    Prev
    Next
    INDEX
    Explanations

    counterparty risk

    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_5_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
    س
    1.87
    ح
    1.42
    أ
    1.24
    很
    1.23
    大
    1.19
    不
    1.17
    可以
    1.16
    Про
    1.15
    高
    1.10
    時候
    1.08
    POSITIVE LOGITS
    ть
    1.46
    ar
    1.30
    el
    1.30
    al
    1.16
    ת
    1.13
    দের
    1.12
    ף
    1.12
    ﺔ
    1.12
    л
    1.11
     $
    1.10
    Activations Density 0.000%

    No Known Activations