© 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. 9394
    Prev
    Next
    INDEX
    Explanations

    mentions of Prince Harry and Meghan Markle's wedding anniversary

    oai_token-act-pair · gemini-2.0-flash

    mixed token patterns with varying formats

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

    marriage and relationships

    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
     wife
    -1.05
     husband
    -0.94
     Wife
    -0.92
    wife
    -0.86
     WIFE
    -0.85
     Husband
    -0.83
    Wife
    -0.82
    husband
    -0.78
     spouses
    -0.77
     wives
    -0.75
    POSITIVE LOGITS
    ISupport
    0.68
     ویکی‌پدیای
    0.58
    
    0.54
    ulario
    0.46
    valdi
    0.45
     eldest
    0.44
    Jaco
    0.44
    <?
    0.43
     root
    0.42
    ChildIndex
    0.42
    Activations Density 0.559%

    No Known Activations