© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13184
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews and mentions of specific meals and food brands.

    oai_token-act-pair · gemini-2.0-flash

    Luxury restaurants/hotels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Wikimedijinoj
    -0.82
    WebServlet
    -0.77
     enfans
    -0.76
     الرياضيه
    -0.75
    GraphicsUnit
    -0.67
     BoxFit
    -0.66
    tagext
    -0.64
     ویکی‌پدیای
    -0.64
     étudi
    -0.63
    featureID
    -0.61
    POSITIVE LOGITS
     hé
    0.52
    +#+#
    0.46
    doctype
    0.45
     boutiques
    0.44
     شان
    0.43
    lismo
    0.43
    inan
    0.43
    inare
    0.42
    सम
    0.42
    walla
    0.42
    Activations Density 3.020%

    No Known Activations