© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    text about the FDA and medicine

    oai_token-act-pair · gemini-2.0-flash

    references to food

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

    Food related

    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
    AutoresizingMask
    -0.67
    ulgação
    -0.60
    fromnode
    -0.59
     DNC
    -0.59
    ptonshire
    -0.57
    日閲覧
    -0.55
     onPostExecute
    -0.54
     ExecuteAsync
    -0.54
     kompres
    -0.54
     initComponents
    -0.54
    POSITIVE LOGITS
     Food
    0.97
    Food
    0.94
     food
    0.89
    Personensuche
    0.81
     FOOD
    0.77
    food
    0.75
     Foods
    0.74
    Foods
    0.72
     foods
    0.71
    FOOD
    0.68
    Activations Density 3.031%

    No Known Activations