© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    sentences about food and morning routines

    oai_token-act-pair · gemini-2.0-flash

    programming terminology related to UI components

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

    breakfast and food

    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
    OGND
    -0.57
    vastava
    -0.55
     Gens
    -0.54
    Билгалдахарш
    -0.54
     endregion
    -0.53
    principalColumn
    -0.52
    spyOn
    -0.51
    QMetaType
    -0.50
     alluminio
    -0.50
     nemlig
    -0.49
    POSITIVE LOGITS
    buttonBar
    0.56
    DockStyle
    0.56
    RegressionTest
    0.55
    tagHelperRunner
    0.51
     Вікі
    0.49
    íté
    0.47
    BarItem
    0.46
    invokeLater
    0.46
    hasMoreElements
    0.46
    RenderAtEndOf
    0.46
    Activations Density 1.667%

    No Known Activations