© 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. 2599
    Prev
    Next
    INDEX
    Explanations

    words and names associated with businesses and organizations

    oai_token-act-pair · gemini-2.0-flash

    set

    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
     NSCoder
    -0.61
    sizeCache
    -0.59
     jadx
    -0.56
    cloudflare
    -0.55
    iNdEx
    -0.55
    destroyAll
    -0.54
    pexpr
    -0.54
    UpInside
    -0.54
    SaveChanges
    -0.54
    typeparam
    -0.54
    POSITIVE LOGITS
     set
    3.61
     Set
    3.14
    set
    2.91
    Set
    2.84
     SET
    2.58
     sets
    2.45
    SET
    2.34
     Sets
    2.20
    セット
    2.06
    sets
    1.99
    Activations Density 5.538%

    No Known Activations