© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 324
    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_12_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
    
    0.48
     执行
    0.47
    一个小
    0.47
    执行
    0.47
     স্টেট
    0.46
    一个
    0.45
     StreamWriter
    0.45
    鹿
    0.43
    STATE
    0.43
     Screenshot
    0.42
    POSITIVE LOGITS
     altijd
    0.38
    แรง
    0.38
     오래
    0.37
     aldrig
    0.37
     länger
    0.37
    riving
    0.36
     अक्सर
    0.36
    세요
    0.36
     lange
    0.36
     altid
    0.36
    Activations Density 0.003%

    No Known Activations