© 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. 660
    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
     admirably
    1.86
     ð
    1.79
     recourse
    1.64
    ErrorClazz
    1.57
     perfectly
    1.52
     assortment
    1.50
    Основ
    1.49
    (|
    1.49
     hailing
    1.48
     việc
    1.47
    POSITIVE LOGITS
    实话
    2.18
    不定
    1.97
     goodbye
    1.83
    াল
    1.70
    locale
    1.65
    tale
    1.60
     hello
    1.56
     πως
    1.53
     ότι
    1.50
     বাহুল্য
    1.48
    Activations Density 0.248%

    No Known Activations