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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 4562
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to mathematical or scientific equations, theories, and proofs

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     تعدى
    -0.65
    ...");
    -0.59
     resourceCulture
    -0.56
    ']));
    -0.54
     "));
    -0.53
    enchymal
    -0.51
     ());
    -0.51
    chymal
    -0.50
    makeConstraints
    -0.50
    榄
    -0.49
    POSITIVE LOGITS
    <bos>
    1.21
    GenerationType
    0.70
    __":
    
    0.55
     بيها
    0.55
    Personendaten
    0.52
     postIndex
    0.52
     flattening
    0.52
    __':
    
    0.50
     eorum
    0.50
     quæ
    0.49
    Activations Density 1.080%

    No Known Activations