© 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. 9081
    Prev
    Next
    INDEX
    Explanations

    away

    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
    िंग
    2.50
    𝔱
    2.45
    ﺒ
    2.39
    
    2.36
    arı
    2.36
    يين
    2.33
    iene
    2.26
    و
    2.22
    ગ
    2.22
    да
    2.20
    POSITIVE LOGITS
    ように
    3.27
     moveable
    3.14
    س
    2.95
     управлять
    2.61
    ть
    2.47
    
    2.46
     conforman
    2.43
     movable
    2.43
    ství
    2.42
     власти
    2.42
    Activations Density 0.007%

    No Known Activations