© 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. 7707
    Prev
    Next
    INDEX
    Explanations

    seemingly random two or three letter acronyms

    oai_token-act-pair · gemini-2.0-flash

    words with an archaic or formal style

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

    acronyms and abbreviations

    np_max-act-logits · gemini-2.0-flash

    state abbreviations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ,
    -0.80
     
    -0.79
    ↵
    -0.79
     I
    -0.73
      
    -0.70
     (
    -0.70
    .
    -0.69
    ↵↵
    -0.68
     in
    -0.66
    <eos>
    -0.62
    POSITIVE LOGITS
     Efq
    1.64
     itſelf
    1.47
     Monfieur
    1.39
     myſelf
    1.32
     houſe
    1.28
     Jefus
    1.27
     faſt
    1.27
     Majefty
    1.24
     ſever
    1.24
     auffi
    1.23
    Activations Density 2.804%

    No Known Activations