© 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. 7186
    Prev
    Next
    INDEX
    Explanations

    somewhat common, but distinct, phrases, and potentially ISBN/location codes in a book.

    oai_token-act-pair · 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
     book
    -3.16
    book
    -2.77
     Book
    -2.73
    Book
    -2.70
     BOOK
    -2.56
    BOOK
    -2.45
     books
    -2.42
    books
    -2.27
    Books
    -2.25
     Books
    -2.20
    POSITIVE LOGITS
    SequentialGroup
    0.56
    BuilderFactory
    0.54
     CHtml
    0.52
    ScopeManager
    0.50
    NegativeButton
    0.48
     continúas
    0.48
    versaire
    0.47
     absl
    0.46
    acons
    0.44
    beforeEach
    0.44
    Activations Density 1.709%

    No Known Activations