© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9299
    Prev
    Next
    INDEX
    Explanations

    words related to purchasing items, levels, vendors, patterns, and quests in the World of Warcraft

    oai_token-act-pair · gemini-2.0-flash

    video games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.66
     fubject
    -0.64
     bogotá
    -0.62
     houſe
    -0.58
     himſelf
    -0.52
     purpoſe
    -0.52
     reaſon
    -0.51
     myſelf
    -0.50
     ſol
    -0.50
     themſelves
    -0.50
    POSITIVE LOGITS
    __(/*!
    0.78
    PhysRev
    0.61
    
    0.59
    --]
    0.57
    Демографія
    0.57
     AssemblyCompany
    0.57
    IRO
    0.56
    omed
    0.56
     FontWeight
    0.56
    IsContent
    0.56
    Activations Density 13.341%

    No Known Activations