© 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. 36590
    Prev
    Next
    INDEX
    Explanations

    Michael 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
    t
    0.97
    ت
    0.80
    ان
    0.80
    il
    0.78
    ak
    0.76
    ти
    0.74
    ul
    0.70
    ir
    0.70
    <0x0D>
    0.70
    т
    0.70
    POSITIVE LOGITS
    Zespół
    0.73
     be
    0.64
     kaynağından
    0.63
     Fonbet
    0.61
    ם
    0.61
    MS
    0.60
     întreb
    0.59
     atteinte
    0.59
    çada
    0.59
     alemán
    0.59
    Activations Density 0.001%

    No Known Activations