© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14827
    Prev
    Next
    INDEX
    Explanations

    the word "Pay", especially in the context of "Pay Per Click" advertising or healthcare payments

    oai_token-act-pair · gemini-2.0-flash

    references to payment or cost-related terms

    np_token-act-pair-logits · gpt-4o-mini

    pay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IsContent
    -0.78
     propOrder
    -0.76
    ItemLayout
    -0.72
    IContainer
    -0.69
    SharedCtor
    -0.66
     Bioaccumulative
    -0.66
    webElementXpaths
    -0.65
    insee
    -0.64
     informée
    -0.63
     AssemblyTitle
    -0.62
    POSITIVE LOGITS
    ต่อ
    0.44
    didSet
    0.43
    less
    0.42
     costante
    0.40
    روزی
    0.40
     educativas
    0.40
     segreto
    0.40
     tæ
    0.40
     sociaux
    0.39
     lieux
    0.39
    Activations Density 0.370%

    No Known Activations