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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36528
    Prev
    Next
    INDEX
    Explanations

    multilingual phrases with negation

    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_3_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
    ية
    0.82
    ки
    0.70
    ০
    0.69
    ة
    0.68
    اً
    0.66
    মেন্ট
    0.64
    um
    0.63
    нг
    0.63
    اي
    0.62
    кої
    0.60
    POSITIVE LOGITS
     is
    0.73
     math
    0.72
     $
    0.68
     synthesized
    0.66
    ↵
    0.65
     transform
    0.64
     north
    0.64
     historian
    0.62
     page
    0.61
     margin
    0.60
    Activations Density 0.000%

    No Known Activations