© 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. 13643
    Prev
    Next
    INDEX
    Explanations

    words related to data and experiment parameters, including number-related words

    oai_token-act-pair · gemini-2.0-flash

    data records/passage

    np_max-act · 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
    cshtml
    -0.66
     Signalez
    -0.63
    ",&
    -0.63
    lessly
    -0.63
    ValueStyle
    -0.62
     EnglishChoose
    -0.61
    ărul
    -0.59
    matchCondition
    -0.59
    twimg
    -0.59
    makeText
    -0.56
    POSITIVE LOGITS
    richTextPanel
    0.64
     kasarigan
    0.58
    رشف
    0.56
    Tôi
    0.52
     فوت
    0.48
    ValueGeneration
    0.47
    tôi
    0.46
     bienvenue
    0.45
    бурга
    0.45
    expandindo
    0.45
    Activations Density 11.624%

    No Known Activations