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

    Neuronpedia

    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. 349
    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
    с
    1.51
     arada
    1.43
    কেন্ড
    1.42
    д
    1.41
    mos
    1.34
    puts
    1.34
     lahan
    1.32
    ൻസ്
    1.32
    uniqueItems
    1.31
    ฀
    1.30
    POSITIVE LOGITS
    ির
    1.56
    റ്റ്
    1.48
    ..--..--
    1.38
    ји
    1.37
    el
    1.36
    categorie
    1.35
    깐
    1.34
     corroborate
    1.33
    intersect
    1.33
    এটি
    1.31
    Activations Density 0.138%

    No Known Activations