© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7576
    Prev
    Next
    INDEX
    Explanations

    foreign words and diverse terms

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     accounted
    0.40
    ipped
    0.38
    Fetching
    0.36
     remembered
    0.35
    CRIPTION
    0.34
    atering
    0.34
     गिरि
    0.34
    ěř
    0.34
    贓
    0.34
    ότητας
    0.34
    POSITIVE LOGITS
     чай
    0.43
    馥
    0.43
     поля
    0.43
    वाती
    0.39
     trwa
    0.39
    色々
    0.39
    苎
    0.38
     allere
    0.37
    щь
    0.37
     खोला
    0.37
    Activations Density 0.002%

    No Known Activations