© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170477
    Prev
    Next
    INDEX
    Explanations

    infant development and actions

    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_20_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
    Million
    0.46
    σκευ
    0.45
    Kre
    0.45
     exaggerated
    0.45
    handleSubmit
    0.45
     costly
    0.44
    ляю
    0.44
    Made
    0.43
    Megan
    0.43
    勾
    0.43
    POSITIVE LOGITS
    obos
    0.44
     Varn
    0.42
     vara
    0.41
    omos
    0.40
     þe
    0.39
    utivo
    0.39
    кугӀ
    0.38
     Cortés
    0.38
    icion
    0.37
     convirt
    0.37
    Activations Density 0.003%

    No Known Activations