© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4762
    Prev
    Next
    INDEX
    Explanations

    words related to food and dining-out experiences

    oai_token-act-pair · gemini-2.0-flash

    food sides and drinks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    IntoConstraints
    -0.71
    DockStyle
    -0.70
    errHandler
    -0.69
    ImageContext
    -0.68
    routeProvider
    -0.68
     kiện
    -0.64
     مشين
    -0.62
     resourceCulture
    -0.60
     financière
    -0.60
    uisine
    -0.59
    POSITIVE LOGITS
     side
    0.79
     Side
    0.70
     sides
    0.61
    Side
    0.60
     SIDE
    0.59
    side
    0.58
     drink
    0.56
    SIDE
    0.51
    FontOfSize
    0.50
     Drink
    0.48
    Activations Density 1.317%

    No Known Activations