© 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. 6992
    Prev
    Next
    INDEX
    Explanations

    legal or judicial opinions and arguments

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "fact"

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

    fact

    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
    UpInside
    -0.61
     betweenstory
    -0.57
    raison
    -0.53
     Condi
    -0.49
     Leth
    -0.48
    رشف
    -0.48
    chutz
    -0.47
    InjectAttribute
    -0.47
    hamcrest
    -0.46
    createCanvas
    -0.46
    POSITIVE LOGITS
     facts
    1.34
    facts
    1.04
     Facts
    1.03
    Facts
    1.03
    FACTS
    1.00
     FACTS
    0.98
     factual
    0.87
    fact
    0.84
    Fact
    0.84
     Fact
    0.82
    Activations Density 3.765%

    No Known Activations