© 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. 5158
    Prev
    Next
    INDEX
    Explanations

    the word "you" and other words that usually accompany it, such as "your" and "their"

    oai_token-act-pair · gemini-2.0-flash

    your

    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
     resourceCulture
    -0.73
     propOrder
    -0.70
    ьаж
    -0.69
    KommentareTeilen
    -0.66
     normaux
    -0.63
     AssemblyCulture
    -0.62
    DockStyle
    -0.62
    脚注の使い方
    -0.62
    contentLoaded
    -0.60
     jspb
    -0.59
    POSITIVE LOGITS
    Catégorie
    0.57
     onItemClick
    0.51
     fun
    0.49
    ThemeOverlay
    0.49
    litude
    0.49
     ath
    0.48
     *@
    0.46
     Carmel
    0.46
    IAction
    0.46
     MIMO
    0.45
    Activations Density 2.179%

    No Known Activations