© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13784
    Prev
    Next
    INDEX
    Explanations

    mentions of shopping, sales, and purchasing items

    oai_token-act-pair · gemini-2.0-flash

    terms related to sales

    np_token-act-pair-logits · gpt-4o-mini

    sale

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     كومونز
    -0.84
     Monfieur
    -0.75
     itſelf
    -0.68
    RTDA
    -0.67
    setVerticalGroup
    -0.67
    arakhand
    -0.67
    èdia
    -0.66
     Wikimédia
    -0.66
    titleMargin
    -0.66
     pleaſure
    -0.65
    POSITIVE LOGITS
     sale
    2.36
     Sale
    2.08
    sale
    1.98
    Sale
    1.89
     SALE
    1.79
     sales
    1.68
    SALE
    1.59
     Sales
    1.52
    Sales
    1.43
    sales
    1.39
    Activations Density 1.257%

    No Known Activations