© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9622
    Prev
    Next
    INDEX
    Explanations

    words expressing interrogatives or opinions

    oai_token-act-pair · gemini-2.0-flash

    How

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ReusableCell
    -0.57
    utnant
    -0.57
     propOrder
    -0.55
     Uniti
    -0.54
    hetamine
    -0.54
     Willkommen
    -0.53
     समीक्षक
    -0.50
    onnage
    -0.50
    wts
    -0.49
     تانيه
    -0.48
    POSITIVE LOGITS
     how
    2.20
    how
    1.73
    How
    1.71
     How
    1.70
    HOW
    1.32
     HOW
    1.29
     cómo
    1.25
     bagaimana
    1.24
     كيف
    1.15
     hvordan
    1.11
    Activations Density 0.685%

    No Known Activations