© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    references to time, including years, seasons, months, and durations.

    oai_token-act-pair · gemini-2.0-flash

    Mentions time

    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
    mark
    -0.54
    @[+][
    -0.50
    Mark
    -0.44
    markup
    -0.43
    protoc
    -0.43
     markup
    -0.42
     Mark
    -0.42
     mark
    -0.41
     marqu
    -0.40
    meden
    -0.38
    POSITIVE LOGITS
     autrefois
    0.71
    expandindo
    0.69
     tombé
    0.69
     polaire
    0.69
     appartient
    0.64
     Italie
    0.64
    meant
    0.64
    ModelSerializer
    0.63
     brought
    0.61
    脚注の使い方
    0.61
    Activations Density 2.270%

    No Known Activations