© 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. 6017
    Prev
    Next
    INDEX
    Explanations

    information about how long shipping takes

    oai_token-act-pair · gemini-2.0-flash

    business

    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
     المعيارى
    -0.57
    findById
    -0.47
     Author
    -0.44
     AUTHOR
    -0.44
     pangan
    -0.42
    таки
    -0.42
     CreateTagHelper
    -0.41
     Автор
    -0.41
    Author
    -0.40
    DispatchToProps
    -0.40
    POSITIVE LOGITS
     business
    1.44
    business
    1.29
     Business
    1.13
    Business
    1.13
     BUSINESS
    1.09
     busi
    1.02
     Geschäft
    0.98
    BUSINESS
    0.96
     Geschäfts
    0.93
     working
    0.85
    Activations Density 1.695%

    No Known Activations