© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5950
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "Galafold"

    oai_token-act-pair · gemini-2.0-flash

    Gal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ARA
    -0.52
    Примітки
    -0.51
    +:+
    -0.50
    ara
    -0.49
    nages
    -0.48
    rm
    -0.48
    rena
    -0.47
    ={`
    -0.47
    agens
    -0.47
    randall
    -0.47
    POSITIVE LOGITS
    AccessorTable
    0.75
    OOTDTY
    0.64
    FTFY
    0.62
    expandindo
    0.62
     autorytatywna
    0.62
     متعلقه
    0.60
    SharedDtor
    0.59
    WaitGroup
    0.57
    جغرافيا
    0.56
     poffible
    0.56
    Activations Density 0.397%

    No Known Activations