© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11720
    Prev
    Next
    INDEX
    Explanations

    dry heat and steam

    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_13_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
    ส์
    0.40
    长时间
    0.38
    匙
    0.35
    springframework
    0.35
     হাসিনার
    0.35
     temperament
    0.35
    niejszych
    0.34
     trà
    0.34
     ரசிகர்கள்
    0.34
    chai
    0.33
    POSITIVE LOGITS
     H
    0.50
     Rouen
    0.49
     слот
    0.48
    H
    0.44
     Vocês
    0.44
    ご確認
    0.43
     कुत्तों
    0.42
    М
    0.41
    륙
    0.41
    Созда
    0.41
    Activations Density 0.050%

    No Known Activations