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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2886
    Prev
    Next
    INDEX
    Explanations

    code, laws, news organizations, military operations, and math equations

    oai_token-act-pair · gemini-2.0-flash

    news and technical documents

    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
     Prod
    -0.70
     Produits
    -0.65
     Chất
    -0.62
     Firm
    -0.61
     Produ
    -0.60
    Utili
    -0.60
     Prep
    -0.59
     Prov
    -0.59
    Produce
    -0.59
     Products
    -0.59
    POSITIVE LOGITS
     Three
    0.65
     Two
    0.62
     Seven
    0.59
     chi̍t
    0.59
     Five
    0.56
    sizeCache
    0.55
    Number
    0.54
     Six
    0.54
     Number
    0.53
     Nine
    0.52
    Activations Density 10.837%

    No Known Activations