© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    historical text about the formation of empires, kingdoms, and political rule

    oai_token-act-pair · gemini-2.0-flash

    Feudalism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مرئيه
    -0.94
    IUrlHelper
    -0.93
    ⓧ
    -0.81
     utafitiHapana
    -0.78
    Geplaatst
    -0.77
    WebVitals
    -0.73
     Jefus
    -0.73
     autorytatywna
    -0.70
     بيها
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
     retain
    0.54
     man
    0.52
     lord
    0.52
     Plan
    0.51
     Fe
    0.50
     landed
    0.50
     vi
    0.48
     plan
    0.47
     Ho
    0.46
     Fre
    0.46
    Activations Density 1.674%

    No Known Activations