© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13763
    Prev
    Next
    INDEX
    Explanations

    words that relate to titles, nations, treaties, and research or education departments

    oai_token-act-pair · gemini-2.0-flash

    dukes and empires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Nacionales
    -0.48
    Espèce
    -0.46
    更に
    -0.45
    aol
    -0.45
    cin
    -0.44
     DeL
    -0.44
     diſt
    -0.42
     Waray
    -0.42
     affaires
    -0.42
    th
    -0.42
    POSITIVE LOGITS
    :✨
    0.84
     jScrollPane
    0.79
    IntoConstraints
    0.74
    rawDesc
    0.71
    例句
    0.71
    enterOuterAlt
    0.67
    expandindo
    0.66
     okuyayım
    0.66
    __*/
    0.65
    };*/
    0.64
    Activations Density 2.455%

    No Known Activations