© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256258
    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_10_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
    ية
    1.52
     plumes
    1.15
    kl
    1.13
    তী
    1.07
     fui
    1.06
    ה
    1.05
     straws
    1.04
     branches
    1.04
     dared
    1.03
     tillegg
    1.03
    POSITIVE LOGITS
    мо
    1.35
    <unused14>
    1.26
    <unused10>
    1.23
    cough
    1.22
     успі
    1.22
    cía
    1.21
     "-//
    1.20
     indi
    1.18
     Năm
    1.17
    앤
    1.16
    Activations Density 0.000%

    No Known Activations