© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    text excerpts referring to legal or governmental matters such as acts, laws, rules, treaties, departments, and other legal offenses and jargon.

    oai_token-act-pair · gemini-2.0-flash

    Act/Law

    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
    iastes
    -0.64
    TestingModule
    -0.61
    OGND
    -0.59
    ChildScrollView
    -0.56
     bellows
    -0.56
     tiens
    -0.54
     Palmeiras
    -0.54
    GEBURTSDATUM
    -0.53
    GetAxis
    -0.53
     ويكي
    -0.52
    POSITIVE LOGITS
    __((
    0.68
     continúas
    0.59
     Процитовано
    0.52
     crossorigin
    0.50
    RTSC
    0.48
    (")");
    0.47
    >({
    0.46
    eeded
    0.45
     ("%
    0.45
    rarr
    0.45
    Activations Density 7.129%

    No Known Activations