© 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. 35163
    Prev
    Next
    INDEX
    Explanations

    говорение, прогнозирование, описание

    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
     for
    0.88
     of
    0.75
    ↵↵
    0.69
    d
    0.69
    p
    0.68
    ले
    0.68
    的可
    0.67
    ANG
    0.64
    v
    0.63
    ش
    0.63
    POSITIVE LOGITS
    Ⴎ
    0.69
    araman
    0.67
    esorios
    0.66
    duğ
    0.66
    ۔
    0.65
     yaşad
    0.65
    ducation
    0.64
    ו
    0.64
     पीरिय
    0.63
    quinone
    0.62
    Activations Density 0.000%

    No Known Activations