© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1528
    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
    স
    0.98
    ?>"
    0.97
    ?>
    0.96
     bersifat
    0.94
    Regards
    0.94
    د
    0.93
    م
    0.93
    道府県
    0.89
    у
    0.87
    ι
    0.87
    POSITIVE LOGITS
    cules
    1.11
     fantas
    1.06
     ince
    1.03
     distinta
    0.96
     žel
    0.96
     intestines
    0.95
     capelli
    0.95
     veste
    0.95
     nešto
    0.95
     retinal
    0.94
    Activations Density 0.634%

    No Known Activations