© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15343
    Prev
    Next
    INDEX
    Explanations

    titles with adjectives and nouns

    oai_token-act-pair · gemini-2.0-flash

    tax problems

    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
     iſt
    -0.96
     purpoſe
    -0.91
     initComponents
    -0.91
     myſelf
    -0.91
    \{\\
    -0.88
     uſed
    -0.86
     pleaſure
    -0.85
     ―――――
    -0.84
     
    -0.84
     
    -0.84
    POSITIVE LOGITS
     On
    0.80
     An
    0.77
     In
    0.76
     To
    0.75
     For
    0.74
     At
    0.74
     It
    0.72
     They
    0.72
     One
    0.71
     Their
    0.70
    Activations Density 1.054%

    No Known Activations