© 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. 10958
    Prev
    Next
    INDEX
    Explanations

    code snippets and date/time formatting

    oai_token-act-pair · gemini-2.0-flash

    Time units

    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
    sizeCache
    -0.46
    Hauptartikel
    -0.41
     chó
    -0.41
    nito
    -0.40
    roud
    -0.40
    IBOutlet
    -0.39
     extracellular
    -0.39
     Biotechnology
    -0.38
     Mehl
    -0.37
    ActionMode
    -0.36
    POSITIVE LOGITS
     days
    1.41
     day
    1.41
     month
    1.34
     week
    1.33
     hour
    1.29
     Days
    1.23
     Month
    1.20
     DAYS
    1.20
    week
    1.20
     hours
    1.20
    Activations Density 10.237%

    No Known Activations