© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10916
    Prev
    Next
    INDEX
    Explanations

    words/characters ending in "al","ed","io","yn","ys","by","thy"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ########.
    -0.80
     NUKAT
    -0.68
    IBOutlet
    -0.64
    tagHelperRunner
    -0.62
     perciò
    -0.61
     ویکی‌پدیا
    -0.61
    بوابة
    -0.59
     MainAxisSize
    -0.58
     ویکی‌پدی
    -0.57
    PullParser
    -0.57
    POSITIVE LOGITS
    By
    0.62
     cherchés
    0.54
     By
    0.54
     bye
    0.52
    %</
    0.51
    InitVars
    0.50
    %");
    0.49
    bye
    0.49
     articulo
    0.49
     Bye
    0.47
    Activations Density 0.658%

    No Known Activations