© 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. 38229
    Prev
    Next
    INDEX
    Explanations

    Russian: много, внутри, нет, лет, тебе, воды, лет

    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
     so
    0.59
     v
    0.58
    spiration
    0.56
    ’
    0.56
     s
    0.54
     causing
    0.54
    性
    0.53
    for
    0.53
    erc
    0.53
     accents
    0.52
    POSITIVE LOGITS
    ῎
    0.52
     judíos
    0.50
    ⤠
    0.48
    쾰
    0.47
     nisid
    0.47
    رجال
    0.47
    াহিয়ার
    0.46
     Provisional
    0.46
     investigadores
    0.46
     Mandala
    0.46
    Activations Density 0.014%

    No Known Activations