© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4833
    Prev
    Next
    INDEX
    Explanations

    foreign words and technical scripts

    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_39_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
     കണ്ണ
    0.43
     Engage
    0.41
     প্রতিরোধের
    0.40
     прад
    0.39
    隴
    0.39
     Engagement
    0.38
    engagement
    0.37
     इफेक्ट
    0.37
     حلقات
    0.37
     بابەت
    0.37
    POSITIVE LOGITS
     Amman
    0.40
     rostr
    0.38
     постепенно
    0.37
    हतक
    0.37
     gradually
    0.36
    ›
    0.36
     shew
    0.35
     Ammo
    0.34
    Boot
    0.34
     ecma
    0.34
    Activations Density 0.009%

    No Known Activations