© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    references to regulations

    oai_token-act-pair · gemini-2.0-flash

    specific regulatory terminology and format

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

    legal codes

    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
    hartt
    -0.56
    webElementXpaths
    -0.52
     /\.(
    -0.49
    ցված
    -0.49
    GHIJKLM
    -0.49
    WireFormatLite
    -0.48
     Италијани
    -0.48
    testnet
    -0.48
    PreferredItem
    -0.47
    hasMoreElements
    -0.47
    POSITIVE LOGITS
    ImageContext
    0.72
    tvguidetime
    0.69
    indépendance
    0.59
    SequentialGroup
    0.58
     Infórmanos
    0.56
     intptr
    0.54
     carteles
    0.52
     الحره
    0.52
    lewati
    0.52
    TableField
    0.51
    Activations Density 1.520%

    No Known Activations