© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5296
    Prev
    Next
    INDEX
    Explanations

    words in a mathematical paper

    oai_token-act-pair · gemini-2.0-flash

    mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Италијани
    -1.02
     lenker
    -0.94
    Personensuche
    -0.87
    ItemBackground
    -0.84
     ویکی‌پدی
    -0.80
     kaarangay
    -0.77
     transfieras
    -0.76
    IUrlHelper
    -0.76
    libft
    -0.75
    featureID
    -0.75
    POSITIVE LOGITS
    archiviato
    0.52
     irreducible
    0.49
     Bí
    0.48
     Stateless
    0.46
    없
    0.44
    hfill
    0.43
    InSection
    0.43
    TableRow
    0.42
     אב
    0.42
     Huk
    0.42
    Activations Density 8.125%

    No Known Activations