© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16250
    Prev
    Next
    INDEX
    Explanations

    words in Croatian/Serbian

    oai_token-act-pair · gemini-2.0-flash

    UI text and transliteration

    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
    Brainz
    -0.68
    zijn
    -0.56
    passo
    -0.53
    SuccessListener
    -0.52
    ownic
    -0.52
     sumpay
    -0.52
     دیکھیے
    -0.51
     ویکی‌پدیای
    -0.51
    webElementXpaths
    -0.50
    ไหน
    -0.50
    POSITIVE LOGITS
    #![
    0.49
    kut
    0.49
     incontra
    0.48
     XCTest
    0.47
     rencontre
    0.47
    hode
    0.46
    dymyr
    0.46
     ADI
    0.46
    geb
    0.45
    itul
    0.44
    Activations Density 0.057%

    No Known Activations