© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37497
    Prev
    Next
    INDEX
    Explanations

    bigram models, bitwidths

    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
    UM
    0.73
    UT
    0.69
    ‌های
    0.68
    কে
    0.65
    の原因
    0.63
    ‌هایی
    0.62
    GER
    0.59
    ക
    0.59
    ian
    0.58
    ın
    0.58
    POSITIVE LOGITS
    ו
    0.96
    و
    0.91
    ка
    0.67
     salaried
    0.67
    in
    0.66
    েক
    0.66
    ни
    0.65
    вач
    0.64
    л
    0.64
     ٣
    0.63
    Activations Density 0.002%

    No Known Activations