© 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. 124920
    Prev
    Next
    INDEX
    Explanations

    Mnemosyne, temples, or place 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
    i
    1.09
    ;
    0.89
    <0xB2>
    0.83
    ihe
    0.69
     площа
    0.66
     mikä
    0.65
    เท้า
    0.61
     kilka
    0.61
    <0x80>
    0.61
     demás
    0.60
    POSITIVE LOGITS
    س
    0.87
    ف
    0.86
    s
    0.83
    在
    0.82
    ים
    0.80
    ص
    0.79
    هایی
    0.75
    ের
    0.73
    по
    0.67
    ிரி
    0.67
    Activations Density 0.000%

    No Known Activations