© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10993
    Prev
    Next
    INDEX
    Explanations

    the word "app" or the word "will," often in a context related to software or mobile devices.

    oai_token-act-pair · gemini-2.0-flash

    show or display

    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
    -0.76
    RenderAtEndOf
    -0.73
    MLLoader
    -0.66
    Aiheesta
    -0.66
    ConstraintMaker
    -0.63
    enderror
    -0.63
    oa̍t
    -0.60
    AnchorTagHelper
    -0.58
     GoogleFonts
    -0.57
     SqlParameter
    -0.56
    POSITIVE LOGITS
     displays
    0.55
     show
    0.54
     display
    0.51
     Displays
    0.50
     displaying
    0.49
     pull
    0.48
     shows
    0.47
     DISPLAY
    0.46
     показать
    0.46
     afficher
    0.45
    Activations Density 2.443%

    No Known Activations