© 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. 36747
    Prev
    Next
    INDEX
    Explanations

    try-catch block

    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
    <h2>
    0.77
    ли
    0.70
    )!
    0.60
    មិន
    0.56
    <h3>
    0.56
     tonnes
    0.55
    ণি
    0.54
     terceros
    0.54
    㸮
    0.54
     ix
    0.54
    POSITIVE LOGITS
    s
    1.20
    с
    1.01
    ك
    0.93
    k
    0.89
    a
    0.87
    ка
    0.79
    t
    0.77
    z
    0.76
    на
    0.75
    st
    0.73
    Activations Density 0.002%

    No Known Activations