© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6571
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions in cooking recipes

    oai_token-act-pair · gemini-2.0-flash

    cooking recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ſelf
    -1.04
     Efq
    -0.95
    ſelves
    -0.93
     itſelf
    -0.93
     الحره
    -0.90
     وتسجيلات
    -0.88
     ſta
    -0.87
     himſelf
    -0.87
     للمعارف
    -0.86
     purpoſe
    -0.86
    POSITIVE LOGITS
     cooked
    0.60
     
    0.57
     delicious
    0.56
     kulinar
    0.56
     eaten
    0.55
     culinary
    0.55
    Eater
    0.54
     eater
    0.54
     Restaurant
    0.53
     yummy
    0.52
    Activations Density 1.187%

    No Known Activations