© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15318
    Prev
    Next
    INDEX
    Explanations

    entities such as people, places, and organizations, often with associated information like birthdates, careers, or faculty pages.

    oai_token-act-pair · gemini-2.0-flash

    Bio/Biography

    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
    淆
    -0.51
    ConstraintMaker
    -0.48
    tilian
    -0.46
    lighet
    -0.46
    ության
    -0.45
     jsPsych
    -0.44
    tich
    -0.44
    Abitanti
    -0.44
    vars
    -0.43
    ạ
    -0.43
    POSITIVE LOGITS
     bio
    1.62
     biography
    1.50
    bio
    1.48
     Bio
    1.45
    Bio
    1.34
     autobiography
    1.34
    biography
    1.28
     biographical
    1.27
     biographies
    1.26
     BIO
    1.25
    Activations Density 1.929%

    No Known Activations