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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14396
    Prev
    Next
    INDEX
    Explanations

    code related to health risks

    oai_token-act-pair · gemini-2.0-flash

    medical terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ſp
    -0.68
     reaſon
    -0.63
     ſte
    -0.62
     Monfieur
    -0.61
     juſ
    -0.60
     ſtate
    -0.60
     ſel
    -0.60
     deſt
    -0.60
     ſmall
    -0.60
     ſtre
    -0.59
    POSITIVE LOGITS
    tagHelperRunner
    0.72
     GenerationType
    0.68
    abetes
    0.66
     الحره
    0.65
     برانيه
    0.58
    GenerationType
    0.55
     referenties
    0.53
    หวัด
    0.52
     мәкал
    0.52
    InjectAttribute
    0.51
    Activations Density 0.983%

    No Known Activations