© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45856
    Prev
    Next
    INDEX
    Explanations

    various formats, rules, and symbols

    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_10_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
    م
    0.50
    ре
    0.47
    ব
    0.46
    nungen
    0.46
     மேற்பட்ட
    0.45
     Bevölker
    0.45
     Austr
    0.45
    危機
    0.45
     insurg
    0.44
     mendengar
    0.44
    POSITIVE LOGITS
    Riga
    0.46
    kova
    0.46
    号码
    0.46
     दत्ता
    0.46
     شائع
    0.45
    ukes
    0.45
     ||
    0.44
     tour
    0.44
    Gior
    0.44
     contrary
    0.44
    Activations Density 0.000%

    No Known Activations