© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15232
    Prev
    Next
    INDEX
    Explanations

    when the author uses the word "fact"

    oai_token-act-pair · gemini-2.0-flash

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     fact
    -0.85
    fact
    -0.83
     facts
    -0.82
     fakta
    -0.74
     Fact
    -0.70
    Facts
    -0.69
    Fact
    -0.66
     חיצוניים
    -0.66
     Facts
    -0.65
     feit
    -0.65
    POSITIVE LOGITS
    WebServlet
    0.63
    alnız
    0.56
    +:+
    0.54
     glycerin
    0.51
    PageFactory
    0.50
    dflare
    0.50
    IContainer
    0.50
    twimg
    0.48
    TypedDataSet
    0.46
     Custody
    0.46
    Activations Density 5.018%

    No Known Activations