© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5294
    Prev
    Next
    INDEX
    Explanations

    It looks like this neuron is activated by code snippets and XML-like file syntax

    oai_token-act-pair · gemini-2.0-flash

    coding variables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     promotion
    -0.56
    arbox
    -0.49
     promotions
    -0.47
    ADEM
    -0.47
    Архівовано
    -0.46
     promoted
    -0.46
    msh
    -0.45
    льтра
    -0.45
     Stock
    -0.44
     Promotion
    -0.44
    POSITIVE LOGITS
    principalTable
    0.61
    Poloha
    0.61
    CodedInputStream
    0.57
    出版年
    0.57
    ByVersion
    0.57
    IGraphics
    0.55
    ắp
    0.52
     Exactos
    0.52
     compañero
    0.51
    UnitTesting
    0.51
    Activations Density 0.341%

    No Known Activations