© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38200
    Prev
    Next
    INDEX
    Explanations

    for the first time in

    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
    ડા
    0.63
     денег
    0.63
    ی
    0.61
    खर
    0.61
     രാജ്യ
    0.61
    Между
    0.59
     kilomètres
    0.59
     villages
    0.59
    村
    0.59
    ب
    0.57
    POSITIVE LOGITS
    augmented
    0.63
    ordinary
    0.57
    augmentation
    0.52
     Augmented
    0.52
    jande
    0.51
     augment
    0.51
    atomic
    0.50
     επι
    0.50
    odisc
    0.50
     augmentation
    0.49
    Activations Density 0.004%

    No Known Activations