© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4405
    Prev
    Next
    INDEX
    Explanations

    code relating to function definitions and variable casting

    oai_token-act-pair · gemini-2.0-flash

    chain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    EMPLO
    -0.65
     Assignee
    -0.64
    webElementXpaths
    -0.64
     ویکی‌پدیای
    -0.62
     يتيمه
    -0.60
     CreateTagHelper
    -0.59
    :✨
    -0.57
     Zacks
    -0.57
    >--}}
    -0.56
     Италијани
    -0.55
    POSITIVE LOGITS
    <bos>
    0.72
     NFT
    0.65
     Bitcoin
    0.65
    openzeppelin
    0.64
     Ethereum
    0.60
     cryptocurrency
    0.58
     NFTs
    0.58
    stateMutability
    0.57
     DeFi
    0.56
     BytesLike
    0.56
    Activations Density 3.286%

    No Known Activations