© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15208
    Prev
    Next
    INDEX
    Explanations

    content related to the World of Warcraft game

    oai_token-act-pair · gemini-2.0-flash

    Variations of "build"

    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
     BorderRadius
    -0.62
    NameInMap
    -0.60
    InputBorder
    -0.58
     boto
    -0.57
     heapq
    -0.57
     nakalista
    -0.55
    complexType
    -0.54
     useHistory
    -0.50
    mybatisplus
    -0.49
     sessionFactory
    -0.49
    POSITIVE LOGITS
     build
    1.27
     builds
    1.13
     Build
    1.09
     load
    1.02
    build
    0.99
     Builds
    0.96
    Build
    0.94
    builds
    0.87
     buildup
    0.84
     Load
    0.84
    Activations Density 1.809%

    No Known Activations