© 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. 107388
    Prev
    Next
    INDEX
    Explanations

    Blackjack

    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_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
    ні
    1.12
    ामध्ये
    1.07
    いた
    1.04
    ız
    0.98
    すすめ
    0.95
     pubblic
    0.93
    YL
    0.92
    ム
    0.91
    лі
    0.91
    Y
    0.90
    POSITIVE LOGITS
    is
    2.09
    ت
    2.03
    at
    1.56
    n
    1.55
    ق
    1.53
    是
    1.50
    는
    1.45
    ر
    1.44
    k
    1.42
    il
    1.41
    Activations Density 0.000%

    No Known Activations