© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    words related to military accolades and prominent figures

    oai_token-act-pair · gemini-2.0-flash

    Military ranks/officers

    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
    psack
    -0.81
     military
    -0.73
    makeConstraints
    -0.69
     RAF
    -0.68
     Soldiers
    -0.67
    LookAnd
    -0.67
    Soldiers
    -0.65
    Military
    -0.65
    __":
    -0.65
     navy
    -0.64
    POSITIVE LOGITS
     Quarter
    0.44
    WebMethod
    0.42
    Mas
    0.41
    vane
    0.40
    Quarter
    0.40
    Everywhere
    0.38
    mask
    0.37
    etter
    0.36
    Short
    0.36
     Short
    0.36
    Activations Density 0.446%

    No Known Activations