© 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. 796
    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
    laughs
    0.37
    ুদ্র
    0.37
    हारी
    0.37
    ן
    0.36
    ا
    0.36
     gali
    0.35
    কেন্ড
    0.35
    ה
    0.34
    ITIONAL
    0.34
     fellow
    0.34
    POSITIVE LOGITS
    𝑠
    0.43
    𝑑
    0.43
    𝑖
    0.40
    ალა
    0.36
    lijke
    0.35
    cial
    0.34
    𝑙
    0.34
    𝑢
    0.33
    нович
    0.32
    ную
    0.32
    Activations Density 0.002%

    No Known Activations