© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203263
    Prev
    Next
    INDEX
    Explanations

    consent knowledge trust confidence

    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_37_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
    ُو
    0.43
     หาร
    0.41
    鋤
    0.40
     palo
    0.38
    укра
    0.37
     вопрос
    0.37
    стые
    0.37
     попробовать
    0.36
    赟
    0.36
    犇
    0.35
    POSITIVE LOGITS
     support
    0.90
    support
    0.80
     Unterstützung
    0.77
     cooperation
    0.73
     Zustimmung
    0.72
     Support
    0.71
     সমর্থন
    0.71
    的支持
    0.71
     apoio
    0.71
     समर्थन
    0.70
    Activations Density 0.002%

    No Known Activations