© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    س
    1.95
    b
    1.52
    ع
    1.49
    ہ
    1.49
    ک
    1.44
    ский
    1.41
    ס
    1.38
    c
    1.33
    AD
    1.28
    EN
    1.23
    POSITIVE LOGITS
    <0x0D>
    1.07
    ларга
    1.05
    lardı
    1.02
     intérieure
    1.00
    getType
    0.97
    <unused973>
    0.94
    рованы
    0.93
     obsług
    0.90
    ljenje
    0.90
    се
    0.90
    Activations Density 0.000%

    No Known Activations