© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175998
    Prev
    Next
    INDEX
    Explanations

    programming and Hindi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     SHO
    0.91
     shu
    0.89
     should
    0.88
     sh
    0.87
     Shou
    0.85
    SHO
    0.85
    should
    0.82
    숄
    0.82
     Шо
    0.82
     شو
    0.81
    POSITIVE LOGITS
     लगाएंगे
    0.36
     اتر
    0.36
     रहेंगे
    0.36
    我们需要
    0.35
    gatsby
    0.35
    하려고
    0.35
     গিয়াছেন
    0.34
    ")}}'
    0.34
     ಮಾಡಲು
    0.34
     ILLINOIS
    0.34
    Activations Density 0.028%

    No Known Activations