© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3756
    Prev
    Next
    INDEX
    Explanations

    the word "offer" and its inflections, and words related to competing proposals such as "winning" and "quote"

    oai_token-act-pair · gemini-2.0-flash

    offer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     offer
    -2.20
     offers
    -1.97
    Offer
    -1.91
     Offer
    -1.87
     offering
    -1.87
    offer
    -1.80
     OFFER
    -1.78
     offered
    -1.75
    offers
    -1.74
     Offers
    -1.72
    POSITIVE LOGITS
     continuant
    0.69
    initializeApp
    0.61
     récents
    0.59
    ientí
    0.58
     Bete
    0.54
     feroit
    0.54
     MaterialApp
    0.54
    DataMember
    0.54
     sélectionnés
    0.53
     démocr
    0.53
    Activations Density 2.021%

    No Known Activations