© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123264
    Prev
    Next
    INDEX
    Explanations

    Giza and Git LFS

    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_3_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
     considerar
    0.68
     decomp
    0.64
     expresar
    0.63
     unusable
    0.63
     fres
    0.63
    졔
    0.63
    ０
    0.62
     одна
    0.61
     る
    0.61
     кў
    0.61
    POSITIVE LOGITS
    ;
    0.91
    ح
    0.90
    n
    0.89
    ন
    0.89
    人
    0.88
    م
    0.88
    ing
    0.86
    ن
    0.79
    ALL
    0.74
    sulf
    0.74
    Activations Density 0.000%

    No Known Activations