© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3742
    Prev
    Next
    INDEX
    Explanations

    phrases and code from a wide variety of programming languages, including C, PHP, and Java

    oai_token-act-pair · gemini-2.0-flash

    coding datatypes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     незавершена
    -0.57
    <bos>
    -0.52
     continuant
    -0.50
    Portail
    -0.45
     disambiguazione
    -0.44
    λευτα
    -0.43
     In
    -0.43
     plus
    -0.42
    strcmp
    -0.41
     turn
    -0.40
    POSITIVE LOGITS
     Baillargeon
    0.75
    encodeWith
    0.71
    UserScript
    0.69
    ISupport
    0.69
    posedge
    0.68
    fml
    0.68
    SequentialGroup
    0.63
    ühen
    0.62
    writeFieldEnd
    0.61
     >=",
    0.61
    Activations Density 0.924%

    No Known Activations