© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44249
    Prev
    Next
    INDEX
    Explanations

    Saudize workforce, nationals preferred

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neglig
    0.41
     Stability
    0.41
     spoj
    0.41
     mene
    0.38
     mik
    0.38
     $
    0.38
     pog
    0.37
     hyg
    0.37
     wetter
    0.36
     mickey
    0.36
    POSITIVE LOGITS
     现在
    0.47
    。</
    0.44
    优先
    0.43
    投标文件
    0.43
     laud
    0.42
     चाहते
    0.41
    лица
    0.41
    第一个
    0.41
    保护
    0.40
    тации
    0.40
    Activations Density 0.002%

    No Known Activations