© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12327
    Prev
    Next
    INDEX
    Explanations

    programming code, focusing on date formats, database operations, and shell scripting elements

    oai_token-act-pair · gemini-2.0-flash

    terms related to time

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

    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_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
    RequestMethod
    -0.52
    moine
    -0.50
    PhysRevD
    -0.48
     mergeFrom
    -0.47
    jeev
    -0.47
    SceneManagement
    -0.46
    addis
    -0.45
    WebVitals
    -0.45
    xFFFFFFFF
    -0.44
    ramine
    -0.43
    POSITIVE LOGITS
    Time
    0.73
     time
    0.73
     Time
    0.70
     setTime
    0.66
    time
    0.64
     TIME
    0.63
     Waktu
    0.63
    awtextra
    0.60
    TIME
    0.59
    σθαι
    0.59
    Activations Density 6.388%

    No Known Activations