© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6403
    Prev
    Next
    INDEX
    Explanations

    words related to prevention, intervention, or protective actions regarding health, safety, or environmental concerns.

    oai_token-act-pair · gemini-2.0-flash

    terms related to measures and interventions

    np_token-act-pair-logits · gpt-4o-mini

    Prevention/Conservation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    mapStateToProps
    -0.65
    ImageContext
    -0.64
    Datuak
    -0.64
    DeleteBehavior
    -0.62
     bezpiecze
    -0.61
     ochron
    -0.61
     estimés
    -0.60
    yntaxException
    -0.60
     Protección
    -0.60
    addCriterion
    -0.60
    POSITIVE LOGITS
     measures
    0.48
     mechanisms
    0.47
     measure
    0.46
     Seel
    0.46
     activities
    0.44
     actuaciones
    0.43
     Measures
    0.42
     planning
    0.42
    semaphore
    0.42
     technologies
    0.41
    Activations Density 1.929%

    No Known Activations