© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11916
    Prev
    Next
    INDEX
    Explanations

    instances of 'give' and 'you', usually in the context of someone providing something to someone else

    oai_token-act-pair · gemini-2.0-flash

    food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    hdashline
    -0.62
     varandra
    -0.57
    bigsqcup
    -0.56
    Inspiration
    -0.50
     تعدى
    -0.49
    sqcup
    -0.48
    bigoplus
    -0.48
     مشارکت‌کنندگان
    -0.47
    alım
    -0.47
     refuerzo
    -0.46
    POSITIVE LOGITS
     food
    0.89
     MainAxisSize
    0.82
    food
    0.77
    Food
    0.75
     Food
    0.72
     FOOD
    0.70
    FOOD
    0.65
    MemoryWarning
    0.64
     foods
    0.62
    poons
    0.62
    Activations Density 8.395%

    No Known Activations