© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    phrases about guns, especially associated with the words "has", "built", and "HK"

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and keywords

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

    instruments, tools, parts

    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
    expandindo
    -0.54
    SizeF
    -0.46
    RegressionTest
    -0.43
     مشارکت‌کنندگان
    -0.43
     urbanas
    -0.43
     karna
    -0.43
    enumi
    -0.43
     itſelf
    -0.42
    vats
    -0.42
    Спољашње
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.98
    зулта
    0.82
     تضيفلها
    0.69
    StoryboardSegue
    0.69
     StatelessWidget
    0.63
     nahilalakip
    0.63
    jspx
    0.62
    AndEndTag
    0.60
     Alamofire
    0.59
    قایناق‌لار
    0.59
    Activations Density 0.417%

    No Known Activations