© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44022
    Prev
    Next
    INDEX
    Explanations

    arn: AWS resource names

    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
    a
    0.82
    o
    0.80
    知道
    0.76
    ки
    0.73
     अबाउट
    0.73
     is
    0.73
    त्या
    0.71
     dhe
    0.70
    an
    0.69
     офис
    0.69
    POSITIVE LOGITS
    '
    0.98
    with
    0.92
    ל
    0.89
    ت
    0.87
    تين
    0.83
    ע
    0.80
    تن
    0.79
    াস
    0.78
    ের
    0.77
    ों
    0.76
    Activations Density 0.000%

    No Known Activations