© 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. 36557
    Prev
    Next
    INDEX
    Explanations

    auto generation and deletion

    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
    0.77
    E
    0.72
    はじめ
    0.66
    야
    0.66
    (%
    0.65
    ए
    0.65
    にっいて
    0.64
    activ
    0.63
    Τα
    0.63
    imeter
    0.63
    POSITIVE LOGITS
    ua
    0.86
    не
    0.82
    心灵
    0.80
    se
    0.75
    ти
    0.73
    landı
    0.67
    ک
    0.67
    ü
    0.66
    uh
    0.64
    是
    0.64
    Activations Density 0.009%

    No Known Activations