© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lol" and some other code-related terms, possibly identifying code examples or discussions

    oai_token-act-pair · gemini-2.0-flash

    lol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -2.05
     Theſe
    -1.95
     Efq
    -1.89
     itſelf
    -1.79
     Jefus
    -1.77
     Majefty
    -1.69
     Monfieur
    -1.67
     themſelves
    -1.66
     uſed
    -1.66
     Houſe
    -1.65
    POSITIVE LOGITS
     
    1.09
    ,
    0.95
     (
    0.87
     we
    0.84
    <eos>
    0.81
     in
    0.80
      
    0.75
     so
    0.74
     w
    0.71
     and
    0.71
    Activations Density 1.091%

    No Known Activations