© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    references to books.

    oai_token-act-pair · gemini-2.0-flash

    book

    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
    Попис
    -0.82
    books
    -0.75
    Books
    -0.74
     Books
    -0.71
    book
    -0.70
    BOOKS
    -0.70
    Book
    -0.67
     Book
    -0.67
     books
    -0.67
     BOOKS
    -0.63
    POSITIVE LOGITS
    EDEFAULT
    0.52
    DrawerToggle
    0.50
    Спољашње
    0.50
    Välislingid
    0.48
    Cordialement
    0.46
    weder
    0.44
    IBAction
    0.44
    toggler
    0.43
     cross
    0.43
    nity
    0.42
    Activations Density 1.958%

    No Known Activations