© 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. 709
    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
    ра
    1.61
    но
    1.61
    ி
    1.56
    werte
    1.46
    )?,
    1.42
    образ
    1.42
    دی
    1.42
    prev
    1.40
    )>\
    1.37
     dvě
    1.36
    POSITIVE LOGITS
     indexPath
    1.50
     alumina
    1.46
    LessThan
    1.46
    sklearn
    1.44
     indicado
    1.41
     extinct
    1.40
     usern
    1.40
     encontrarás
    1.39
     stormed
    1.38
     indicada
    1.36
    Activations Density 0.040%

    No Known Activations