© 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. 12281
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those involving parsing and mathematical operations, with a bias towards JavaScript

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     &___
    -0.82
    WriteBarrier
    -0.76
    Filmographie
    -0.70
    apimachinery
    -0.68
    RenderAtEndOf
    -0.67
    jewództ
    -0.66
    DataAnnotations
    -0.66
    Geographie
    -0.65
     незавершена
    -0.65
     ContentValues
    -0.64
    POSITIVE LOGITS
     vot
    0.54
     too
    0.52
    assan
    0.48
     should
    0.48
     portfolios
    0.47
     Bede
    0.46
     undoing
    0.46
     dones
    0.46
    OGND
    0.45
    devServer
    0.45
    Activations Density 2.434%

    No Known Activations