© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13143
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and places in Great Britain and Ireland

    oai_token-act-pair · gemini-2.0-flash

    words starting with '▁'

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

    Sports and players

    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
     myſelf
    -0.93
     متعلقه
    -0.89
    TypedDataSet
    -0.88
     pleaſure
    -0.86
     Efq
    -0.85
     themſelves
    -0.85
     itſelf
    -0.84
     purpoſe
    -0.84
    ագրություններ
    -0.83
     Theſe
    -0.83
    POSITIVE LOGITS
     Man
    0.53
     log
    0.51
     ban
    0.49
     Red
    0.49
     var
    0.49
     del
    0.48
     ja
    0.47
     Bro
    0.47
     Cross
    0.46
     Con
    0.46
    Activations Density 1.237%

    No Known Activations