Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14565
    Prev
    Next
    INDEX
    Explanations

    references to shopping for items in speciality stores and supermarkets

    oai_token-act-pair · gemini-2.0-flash

    local stores, shopping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     shop
    -0.81
     store
    -0.80
    IntoConstraints
    -0.76
     storefront
    -0.75
    store
    -0.72
    NOPQRST
    -0.71
    المكان
    -0.71
     Store
    -0.70
     Roskov
    -0.69
    󠁢
    -0.68
    POSITIVE LOGITS
     relative
    0.47
     Relative
    0.46
     Liar
    0.45
    PMailer
    0.44
    httphttps
    0.44
    EndGlobalSection
    0.44
    relative
    0.44
    Relative
    0.41
     Вер
    0.39
     coinage
    0.39
    Activations Density 0.656%

    No Known Activations