© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13599
    Prev
    Next
    INDEX
    Explanations

    mathematical notation including summation, integrals, and probabilities

    oai_token-act-pair · gemini-2.0-flash

    sum

    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
     Normdatei
    -0.83
     referenties
    -0.80
     unknownFields
    -0.78
    phosa
    -0.77
    SharedCtor
    -0.71
    PerformLayout
    -0.71
    parsedMessage
    -0.71
    ScopeManager
    -0.66
     Efq
    -0.66
    XMLSchema
    -0.66
    POSITIVE LOGITS
    OrUpdate
    0.50
    ariste
    0.48
     AssemblyTitle
    0.46
     ympä
    0.45
    anyakan
    0.44
     gezet
    0.44
    heça
    0.43
    doubleValue
    0.43
     déplacer
    0.43
    <sub>
    0.42
    Activations Density 1.684%

    No Known Activations