© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160098
    Prev
    Next
    INDEX
    Explanations

    Cartoon, Canton, карто

    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
    ح
    1.12
    ના
    1.11
    ری
    1.04
    ාවිත
    0.99
    رو
    0.93
     stessa
    0.88
    2
    0.87
    ח
    0.83
     vontade
    0.82
     internasional
    0.79
    POSITIVE LOGITS
    n
    1.55
    н
    1.52
    is
    1.27
    a
    1.27
    ন
    1.02
    q
    1.00
    *
    0.99
    ר
    0.99
    for
    0.97
    ن
    0.97
    Activations Density 0.001%

    No Known Activations