© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13878
    Prev
    Next
    INDEX
    Explanations

    people moving up or down stairs

    oai_token-act-pair · gemini-2.0-flash

    stairs and steps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ContentAsync
    -0.67
     Lightboxes
    -0.54
    GEBURTSDATUM
    -0.52
    ReusableCell
    -0.51
    TDG
    -0.49
    पया
    -0.49
    AnchorTagHelper
    -0.46
    URLException
    -0.46
    BarStyle
    -0.46
     suivants
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.57
    moiselle
    0.54
    transQ
    0.52
    unkel
    0.50
    Retail
    0.50
    <![
    0.50
    stadium
    0.50
    Архівовано
    0.50
    entir
    0.49
    labelControl
    0.49
    Activations Density 0.778%

    No Known Activations