© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10980
    Prev
    Next
    INDEX
    Explanations

    code snippets referencing "product" from JavaScript and C# code

    oai_token-act-pair · gemini-2.0-flash

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     product
    -2.48
    product
    -2.41
     Product
    -2.33
    Product
    -2.31
     PRODUCT
    -1.78
     producto
    -1.75
     products
    -1.70
    PRODUCT
    -1.66
    products
    -1.63
     Products
    -1.63
    POSITIVE LOGITS
    Vidite
    0.66
    RectangleBorder
    0.65
    ]=="
    0.63
     ellers
    0.63
    :]:
    0.62
    rungsseite
    0.59
     незавершена
    0.59
     nakalista
    0.58
    ("/:
    0.58
     étrang
    0.57
    Activations Density 0.254%

    No Known Activations