© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12123
    Prev
    Next
    INDEX
    Explanations

    marketing language related to sales and advertising

    oai_token-act-pair · gemini-2.0-flash

    offer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مرئيه
    -0.74
     Majefty
    -0.71
     EconPapers
    -0.62
     ſy
    -0.60
     ſever
    -0.59
    AddTagHelper
    -0.58
    ſelves
    -0.57
    
    -0.57
     ویکی‌پدیا
    -0.57
     Efq
    -0.56
    POSITIVE LOGITS
     offer
    2.00
     Offer
    1.90
     offers
    1.84
    offers
    1.78
    offer
    1.77
     Offers
    1.77
    Offer
    1.76
    Offers
    1.71
     OFFER
    1.61
    OFFER
    1.51
    Activations Density 1.469%

    No Known Activations