© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4574
    Prev
    Next
    INDEX
    Explanations

    mentions of discounts, coupons or deals including percentages and currency symbols

    oai_token-act-pair · gemini-2.0-flash

    coupons and discounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     discount
    -2.05
     Discount
    -1.81
     discounted
    -1.80
     discounts
    -1.78
    discount
    -1.76
    Discount
    -1.70
     Discounts
    -1.63
    Discounts
    -1.60
     discounting
    -1.59
     coupon
    -1.42
    POSITIVE LOGITS
     onCreateView
    0.56
    mą
    0.48
    anches
    0.48
     EconPapers
    0.47
    Vidite
    0.47
     Babel
    0.44
     withRouter
    0.44
    Personensuche
    0.44
    kubectl
    0.43
     tickle
    0.42
    Activations Density 1.099%

    No Known Activations