© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2023
    Prev
    Next
    INDEX
    Explanations

    words related to farming and also religious words within the same document

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    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
    IBarButtonItem
    -0.69
     propOrder
    -0.68
    expandindo
    -0.65
    findpost
    -0.63
    feed
    -0.62
     CreateTagHelper
    -0.62
     feed
    -0.60
    providedIn
    -0.59
    twimg
    -0.57
     Feed
    -0.56
    POSITIVE LOGITS
    Conservation
    0.49
    couvrez
    0.45
    AutoresizingMask
    0.45
    RESOURCES
    0.45
     Conservation
    0.45
    conservation
    0.44
     teléfonos
    0.43
    zaamheid
    0.43
    modelBuilder
    0.43
    DropTable
    0.42
    Activations Density 1.759%

    No Known Activations