© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4237
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     aniline
    2.69
    ⎡
    2.38
     Belediyesi
    2.38
    ﺖ
    2.37
     reimbursed
    2.35
    অ্যাপ
    2.27
    Ingrese
    2.27
     októ
    2.27
    cohort
    2.24
    yana
    2.23
    POSITIVE LOGITS
     gern
    2.54
    мер
    2.49
    ع
    2.49
    ุ่น
    2.32
    ات
    2.31
    いう
    2.25
    विज्ञान
    2.22
    ترین
    2.18
    
    2.15
    е
    2.13
    Activations Density 0.029%

    No Known Activations