© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10720
    Prev
    Next
    INDEX
    Explanations

    words that either refer to an amount of time or words that suggest an event happening over a span of time

    oai_token-act-pair · gemini-2.0-flash

    say units of time/length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     day
    -2.09
     week
    -2.03
     month
    -1.92
     year
    -1.75
     DAY
    -1.64
    day
    -1.61
     Day
    -1.60
     Month
    -1.60
    week
    -1.55
    Day
    -1.54
    POSITIVE LOGITS
    esez
    0.40
    期刊论文
    0.36
    BoxShadow
    0.36
     CreateTagHelper
    0.35
     ActivatedRoute
    0.35
    gsub
    0.34
    addGap
    0.33
     gesche
    0.33
     noDo
    0.33
    WebpackPlugin
    0.33
    Activations Density 13.886%

    No Known Activations