© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12833
    Prev
    Next
    INDEX
    Explanations

    the string "Tk." followed by a number or formatting instructions for drawing figures

    oai_token-act-pair · gemini-2.0-flash

    Miscellaneous text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCompany
    -0.70
    sizeCache
    -0.67
    #+#
    -0.66
     beginnetje
    -0.66
    =$?
    -0.60
    Portale
    -0.60
    ⓧ
    -0.59
    invokeLater
    -0.59
    astify
    -0.59
     незавершена
    -0.59
    POSITIVE LOGITS
     Eud
    0.48
     bid
    0.45
     multilateral
    0.45
    จุ
    0.44
     viață
    0.42
    酵
    0.41
    ждую
    0.41
    endaft
    0.41
     сде
    0.40
     mouseClicked
    0.40
    Activations Density 0.237%

    No Known Activations