© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting the existence of rules or laws, their enforcement, or the lack thereof.

    oai_token-act-pair · gemini-2.0-flash

    terms related to violations or lifting of restrictions

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

    rules or boundaries broken

    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
     nahilalakip
    -0.62
    DoubleQuotes
    -0.57
     שוליים
    -0.56
    بوابة
    -0.52
    Excluded
    -0.51
    BagConstraints
    -0.50
     Inhibit
    -0.49
    Covered
    -0.48
     Allowed
    -0.48
     Inhibition
    -0.47
    POSITIVE LOGITS
     breached
    0.93
     violated
    0.89
     broken
    0.89
     lifted
    0.82
     fulfilled
    0.77
    broken
    0.77
     satisfied
    0.73
    Broken
    0.72
     breach
    0.70
     Broken
    0.69
    Activations Density 3.498%

    No Known Activations