© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    events happening at doors, particularly knocking and entering

    oai_token-act-pair · gemini-2.0-flash

    Entrances and beginnings

    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
    MethodManager
    -0.59
    ctez
    -0.52
    籤
    -0.51
    NameInMap
    -0.49
    ximity
    -0.49
     समीक्षाओं
    -0.49
    تقاوى
    -0.48
    ciec
    -0.47
    
    -0.47
     withdrawal
    -0.46
    POSITIVE LOGITS
     BIBSYS
    0.65
     at
    0.62
     step
    0.55
    addGap
    0.55
    はじめに
    0.54
    AnchorStyles
    0.54
     AssemblyTitle
    0.54
     pasos
    0.52
     Step
    0.52
    Step
    0.52
    Activations Density 0.783%

    No Known Activations