© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9780
    Prev
    Next
    INDEX
    Explanations

    military, police, and government forces acting against some group or individual

    oai_token-act-pair · gemini-2.0-flash

    Military conflicts

    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
     دیکھیے
    -0.64
    ViewImports
    -0.63
     ostavi
    -0.61
     ویکی‌پدی
    -0.61
    GraphicsUnit
    -0.60
     jsPsych
    -0.60
     Abp
    -0.58
    DriverManager
    -0.58
    notations
    -0.57
     danni
    -0.57
    POSITIVE LOGITS
     BoxDecoration
    0.59
     param
    0.51
     mili
    0.46
    oure
    0.43
     riserv
    0.43
     AssemblyProduct
    0.42
     mercenaries
    0.42
     reserve
    0.42
     mer
    0.42
     elite
    0.41
    Activations Density 2.327%

    No Known Activations