© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15330
    Prev
    Next
    INDEX
    Explanations

    words from a diverse set of topics, including technical writing, movie reviews, and business, that indicate some sort of consistent tone

    oai_token-act-pair · gemini-2.0-flash

    throughout

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nahilalakip
    -0.88
     <>",
    -0.82
    ="@+
    -0.77
    WebServlet
    -0.73
    DeleteBehavior
    -0.72
    ыгана
    -0.70
    ThroughAttribute
    -0.70
    complexContent
    -0.69
     snippetHide
    -0.69
     gyhoeddwyd
    -0.69
    POSITIVE LOGITS
     throughout
    2.59
    throughout
    2.36
     Throughout
    2.16
    Throughout
    2.05
     THRO
    1.63
     whole
    1.34
     entire
    1.33
    whole
    1.17
     ganzen
    1.12
     suốt
    1.07
    Activations Density 3.602%

    No Known Activations