© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8482
    Prev
    Next
    INDEX
    Explanations

    words related to health, research and programming

    oai_token-act-pair · gemini-2.0-flash

    uction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ImageContext
    -0.86
     تضيفلها
    -0.84
    tagHelperRunner
    -0.78
    ConstraintMaker
    -0.73
    parsedMessage
    -0.70
    EDEFAULT
    -0.68
    endpush
    -0.67
     Exacts
    -0.67
    出版年
    -0.67
     Chwiliwch
    -0.66
    POSITIVE LOGITS
     الحره
    0.47
    ğer
    0.44
    aság
    0.43
     marins
    0.42
    uai
    0.42
    SequentialGroup
    0.42
    TagMode
    0.42
    thys
    0.41
    devServer
    0.40
    lierten
    0.40
    Activations Density 20.387%

    No Known Activations