© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2603
    Prev
    Next
    INDEX
    Explanations

    words with multiple meanings, often used in technical or abstract contexts

    oai_token-act-pair · gemini-2.0-flash

    say "le"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    MenuInflater
    -0.46
     voks
    -0.46
    ptonshire
    -0.45
     torchvision
    -0.45
     zvyš
    -0.45
    ãng
    -0.44
    getMenuInflater
    -0.43
     Omn
    -0.42
    \}\\
    -0.42
     soeur
    -0.42
    POSITIVE LOGITS
    le
    1.72
    LE
    1.27
    les
    1.02
    led
    0.90
    leman
    0.90
    lemen
    0.86
    ling
    0.83
    leth
    0.81
    leid
    0.75
    AddHtmlAttribute
    0.73
    Activations Density 6.776%

    No Known Activations