© 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. 4171
    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
    های
    2.49
     Theoretically
    2.35
     nochmal
    2.32
     Anspruch
    2.29
    琢
    2.28
    Naturally
    2.27
    д
    2.25
    perimeter
    2.25
    خ
    2.23
     DEALINGS
    2.22
    POSITIVE LOGITS
    ︎
    2.47
    TE
    2.30
     une
    2.29
     ആവശ്യ
    2.28
     moja
    2.26
    まして
    2.24
    acuse
    2.24
    𝕒
    2.21
     odp
    2.19
     anul
    2.18
    Activations Density 0.007%

    No Known Activations