© 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. 4055
    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
    ства
    2.82
     sloping
    2.39
    tida
    2.31
    न
    2.29
    vey
    2.28
    harga
    2.23
    ტერ
    2.21
    ⬜
    2.20
    rét
    2.20
    ν
    2.17
    POSITIVE LOGITS
    т
    2.51
    ую
    2.18
     acontecer
    1.96
     acus
    1.94
    бре
    1.94
    нение
    1.91
     жив
    1.87
    errorHandler
    1.87
     наличи
    1.86
     स्पी
    1.86
    Activations Density 0.001%

    No Known Activations