© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7664
    Prev
    Next
    INDEX
    Explanations

    question words, particularly "what"

    oai_token-act-pair · gemini-2.0-flash

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    TagMode
    -0.74
    RegressionTest
    -0.70
    PROLOG
    -0.69
     ChromeDriver
    -0.68
    titleMargin
    -0.67
    ISupport
    -0.66
    GEBURTSDATUM
    -0.65
    XmlAccessorType
    -0.65
     createState
    -0.65
     simplifié
    -0.63
    POSITIVE LOGITS
     about
    0.56
     do
    0.54
     blanches
    0.49
    予備
    0.46
     stør
    0.46
     anteriore
    0.45
    ?
    0.44
     chré
    0.44
     does
    0.43
     svenska
    0.43
    Activations Density 0.513%

    No Known Activations