© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12458
    Prev
    Next
    INDEX
    Explanations

    the word "guard"

    oai_token-act-pair · gemini-2.0-flash

    guard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     guard
    -3.14
    guard
    -2.81
     Guard
    -2.61
    Guard
    -2.39
     guards
    -2.34
     GUARD
    -2.25
    guards
    -2.09
     Guards
    -2.09
    GUARD
    -2.06
     guarding
    -1.70
    POSITIVE LOGITS
    tvguidetime
    0.69
    WithIOException
    0.69
     AssemblyCulture
    0.68
     étoit
    0.68
     Reprint
    0.62
     виправивши
    0.60
    reportWebVitals
    0.60
    AutoField
    0.60
    écnicas
    0.60
     Audiodateien
    0.57
    Activations Density 0.564%

    No Known Activations