© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196249
    Prev
    Next
    INDEX
    Explanations

    pattern recognition

    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_4_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
    Y
    0.76
     for
    0.70
    ن
    0.70
     (
    0.67
    0
    0.64
    T
    0.64
    M
    0.63
    ס
    0.63
    K
    0.60
    BA
    0.59
    POSITIVE LOGITS
    ческие
    0.62
     Министерство
    0.61
     называется
    0.57
     القسم
    0.57
    લા
    0.55
     использование
    0.55
    τές
    0.54
    <0x92>
    0.54
    <0xAC>
    0.54
     इसे
    0.54
    Activations Density 0.001%

    No Known Activations