Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7751
    Prev
    Next
    INDEX
    Explanations

    terms related to antioxidants and free radicals

    oai_token-act-pair · gemini-2.0-flash

    radical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     teeth
    -1.07
     Teeth
    -0.96
    teeth
    -0.90
     dientes
    -0.85
    Teeth
    -0.82
     tooth
    -0.78
     dentes
    -0.75
     gigi
    -0.75
     Zähne
    -0.74
     biting
    -0.72
    POSITIVE LOGITS
    OGND
    0.59
     oxidative
    0.57
     toco
    0.54
    SourceChecksum
    0.54
    twimg
    0.54
     Nordic
    0.51
     lenker
    0.51
     Antioxidant
    0.50
    kheim
    0.50
     antioxid
    0.49
    Activations Density 0.958%

    No Known Activations