© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    references to car racing, especially Formula 1 and Le Mans

    oai_token-act-pair · gemini-2.0-flash

    Motorsports and investors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RegressionTest
    -0.66
     RVA
    -0.63
    . 
    -0.58
     PyLong
    -0.57
     שוליים
    -0.57
    RenderAtEndOf
    -0.54
    UnsafeEnabled
    -0.53
    IGraphics
    -0.51
    databind
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
     démocr
    0.70
    iastes
    0.55
     étrangères
    0.54
     smart
    0.54
     juridiques
    0.50
     Utility
    0.50
     strong
    0.50
    ghold
    0.49
     Strong
    0.48
    eake
    0.48
    Activations Density 0.697%

    No Known Activations