© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10983
    Prev
    Next
    INDEX
    Explanations

    words related to diseases and conditions that are found worldwide

    oai_token-act-pair · gemini-2.0-flash

    worldwide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     nationally
    -1.01
     internationally
    -0.97
     globally
    -0.92
     abroad
    -0.91
     worldwide
    -0.84
     domestically
    -0.79
     locally
    -0.77
     ovunque
    -0.77
     Globally
    -0.77
     Locally
    -0.75
    POSITIVE LOGITS
    pyplot
    0.69
     ExecuteAsync
    0.61
    Xna
    0.60
     mxArray
    0.60
    DockStyle
    0.59
    expandindo
    0.58
    adget
    0.57
    ęgn
    0.57
    livion
    0.54
    CORBA
    0.54
    Activations Density 2.853%

    No Known Activations