© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2535
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Tshirt
    1.32
    ﺔ
    1.31
     IELTS
    1.27
    
    1.27
    
    1.26
     wikiHow
    1.25
     Priya
    1.24
     nurture
    1.22
     mindfulness
    1.20
    iduría
    1.20
    POSITIVE LOGITS
    ra
    1.33
    asInstanceOf
    1.15
     $^{
    1.14
    Enfin
    1.10
    ेश
    1.09
    ri
    1.09
     aikana
    1.07
     veut
    1.07
    ితే
    1.04
    ry
    1.01
    Activations Density 1.350%

    No Known Activations