© 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. 14111
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with programming related concepts, especially those including number literals

    oai_token-act-pair · gemini-2.0-flash

    punctuations and conjunctions

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

    numbers

    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
     itſelf
    -1.13
     الرياضيه
    -1.09
    IntoConstraints
    -1.06
     myſelf
    -1.05
    mybatisplus
    -1.04
     Theſe
    -1.03
     Monfieur
    -0.99
     pleaſure
    -0.96
     Reſ
    -0.94
     ſeveral
    -0.92
    POSITIVE LOGITS
    ,
    0.67
    .
    0.64
     and
    0.62
    -
    0.57
     or
    0.56
    <eos>
    0.50
     in
    0.50
     due
    0.47
     for
    0.47
    !
    0.47
    Activations Density 29.996%

    No Known Activations