© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5700
    Prev
    Next
    INDEX
    Explanations

    years and other historical terms

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     nakalista
    -0.83
    ArgsConstructor
    -0.82
    labelledby
    -0.62
     numberWith
    -0.61
     HasFactory
    -0.61
    וך
    -0.59
    __(/*!
    -0.58
    ControllerAdvice
    -0.57
    InjectAttribute
    -0.56
    DoubleQuotes
    -0.56
    POSITIVE LOGITS
    <bos>
    0.88
     nemlig
    0.60
     namelijk
    0.59
     BoxDecoration
    0.56
     anyway
    0.53
     Whigs
    0.52
     totiž
    0.52
    atshirt
    0.52
    isiä
    0.50
    ofür
    0.50
    Activations Density 1.105%

    No Known Activations