© 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. 11989
    Prev
    Next
    INDEX
    Explanations

    supporting or transitional language.

    oai_token-act-pair · gemini-2.0-flash

    fun and interesting facts

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

    fun facts

    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
    gpl
    -0.57
     CURIAM
    -0.54
     BeautifulSoup
    -0.52
    stoffen
    -0.51
    存于互联网档案馆
    -0.51
     pastures
    -0.50
    ibatis
    -0.50
    eners
    -0.48
    bootstrapcdn
    -0.48
     JUDGE
    -0.47
    POSITIVE LOGITS
     fun
    1.67
     fact
    1.54
    Fun
    1.47
    fun
    1.46
     Fun
    1.42
     facts
    1.33
    fact
    1.31
     FACT
    1.23
     interesting
    1.23
    FUN
    1.20
    Activations Density 1.142%

    No Known Activations