© 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. 126674
    Prev
    Next
    INDEX
    Explanations

    noodles and lasagna

    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
     ਬ
    0.83
     آیا
    0.74
    يا
    0.72
     Մ
    0.72
    ढ़ाई
    0.70
     Более
    0.70
     なお
    0.70
     accedere
    0.70
    ים
    0.69
     ﺍ
    0.69
    POSITIVE LOGITS
    o
    1.46
    an
    1.10
    c
    0.94
    ,
    0.93
    n
    0.92
    u
    0.92
    a
    0.89
    *
    0.89
    ü
    0.89
    IN
    0.86
    Activations Density 0.000%

    No Known Activations