© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9654
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and names of chemical substances

    oai_token-act-pair · gemini-2.0-flash

    unconventional textual patterns or symbols

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

    science/research terms

    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
     onCancelled
    -0.83
     fieldNum
    -0.81
    脚注の使い方
    -0.79
    
    -0.79
     AssemblyVersion
    -0.78
     EconPapers
    -0.76
    sidemargin
    -0.76
    原始内容存档于
    -0.76
     initComponents
    -0.75
    autoreleasepool
    -0.75
    POSITIVE LOGITS
    æder
    0.44
    -(
    0.44
    اته
    0.40
     geval
    0.38
     avven
    0.37
    then
    0.36
     Spectra
    0.36
     thoại
    0.35
     works
    0.35
     décé
    0.35
    Activations Density 2.516%

    No Known Activations