© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3719
    Prev
    Next
    INDEX
    Explanations

    terms involving measurements of time and rates

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to databases or programming

    np_token-act-pair-logits · gpt-4o-mini

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Personensuche
    -0.79
    Personendaten
    -0.62
    setVerticalGroup
    -0.58
    ppuden
    -0.52
     виправивши
    -0.52
     Walkover
    -0.52
    TacToe
    -0.49
    jdons
    -0.48
    orghini
    -0.48
    сылкі
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.70
    queryInterface
    0.59
    InjectAttribute
    0.57
    QMetaType
    0.55
    @[+][
    0.55
    createComponent
    0.55
    explique
    0.54
    IsContent
    0.53
    vode
    0.51
    webElement
    0.50
    Activations Density 2.165%

    No Known Activations