© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3183
    Prev
    Next
    INDEX
    Explanations

    dates and words associated with food, especially sweets and treats.

    oai_token-act-pair · gemini-2.0-flash

    food and history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Chocolate
    -0.80
    Chocolate
    -0.77
     Rice
    -0.76
     Sugar
    -0.75
     Cheese
    -0.72
    Grape
    -0.71
     Wheat
    -0.71
     RICE
    -0.69
    Rice
    -0.68
     Cotton
    -0.68
    POSITIVE LOGITS
     myſelf
    0.85
     itſelf
    0.79
     himſelf
    0.73
     pleaſure
    0.71
     Jefus
    0.71
     houſe
    0.70
     Monfieur
    0.69
     faſt
    0.68
     Anſ
    0.66
     themſelves
    0.65
    Activations Density 2.178%

    No Known Activations