© 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. 15872
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings in Georgia

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
     autorytatywna
    -0.71
     GEORGIA
    -0.62
    batore
    -0.60
    帖最后由
    -0.60
    awtextra
    -0.59
    はじめに
    -0.59
     ostavi
    -0.59
     Georgia
    -0.58
     Plenum
    -0.56
    SourceChecksum
    -0.55
    POSITIVE LOGITS
    PRNewswire
    0.57
     تانيه
    0.54
    HtmlAttribute
    0.48
     Hej
    0.46
    illary
    0.45
     Hal
    0.43
    venor
    0.43
    verwijspagina
    0.43
    popper
    0.43
    cari
    0.42
    Activations Density 0.559%

    No Known Activations