© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12909
    Prev
    Next
    INDEX
    Explanations

    the word "par" followed by words related to sports, academics, and science.

    oai_token-act-pair · gemini-2.0-flash

    par

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     par
    -2.75
     Par
    -2.53
    Par
    -2.50
    par
    -2.41
     PAR
    -2.09
    PAR
    -1.91
     pars
    -1.41
     пара
    -1.39
     Para
    -1.37
    para
    -1.34
    POSITIVE LOGITS
     /\.(
    0.49
    ouldering
    0.46
    antMatchers
    0.44
    kkelen
    0.44
    postDelayed
    0.43
     Manns
    0.43
    addLast
    0.42
    diri
    0.42
    estone
    0.41
     Xunit
    0.41
    Activations Density 5.646%

    No Known Activations