© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    scala object declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    Negative Logits
     đây
    1.68
    तना
    1.52
    ﻲ
    1.47
    𝒄
    1.40
    𝒏
    1.38
    𝒖
    1.38
    ेप
    1.36
    grim
    1.36
    اته
    1.36
    auté
    1.35
    POSITIVE LOGITS
    Survived
    1.71
    ش
    1.69
    ر
    1.66
    ء
    1.60
     twenties
    1.57
     canto
    1.56
     말미암아
    1.54
     च्या
    1.52
     चरणों
    1.51
     липня
    1.50
    Activations Density 0.001%

    No Known Activations