© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59379
    Prev
    Next
    INDEX
    Explanations

    dreaming of

    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_11_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
    ance
    0.77
    ו
    0.74
    u
    0.71
    .
    0.63
    r
    0.62
    ی
    0.61
    ir
    0.60
    สิ้น
    0.58
    ر
    0.58
     residing
    0.56
    POSITIVE LOGITS
    логи
    0.63
     LEAD
    0.61
     MATRIX
    0.61
     পর্যবে
    0.60
     huit
    0.60
    того
    0.58
     Cré
    0.58
    тни
    0.58
     tweaking
    0.58
    Kü
    0.58
    Activations Density 0.002%

    No Known Activations