© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    military units (especially air force) and military operations

    oai_token-act-pair · gemini-2.0-flash

    Command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     DataTypes
    -0.82
     betweenstory
    -0.77
    RegressionTest
    -0.75
     propOrder
    -0.74
    oredCriteria
    -0.72
     ferons
    -0.70
    MessageTagHelper
    -0.66
     كومونز
    -0.65
    setVerticalGroup
    -0.64
     AssemblyTitle
    -0.64
    POSITIVE LOGITS
     Army
    0.78
     military
    0.74
     Navy
    0.72
     Military
    0.70
     civilian
    0.69
    umman
    0.68
    Army
    0.63
     soldiers
    0.63
    military
    0.63
    Military
    0.62
    Activations Density 2.874%

    No Known Activations