© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" and sometimes the word "been"

    oai_token-act-pair · gemini-2.0-flash

    look

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     NSCoder
    -0.69
     متعلقه
    -0.67
     unterkunft
    -0.63
    łami
    -0.63
     Daarna
    -0.63
    ثيق
    -0.59
     ())
    -0.59
    )>=
    -0.59
    acağı
    -0.59
    utsu
    -0.58
    POSITIVE LOGITS
    <bos>
    0.65
    ViewFeatures
    0.65
    openqa
    0.63
    dafx
    0.62
    JsonHelper
    0.57
     EClass
    0.55
    initComponents
    0.55
    queryInterface
    0.55
    bitField
    0.54
    InjectAttribute
    0.54
    Activations Density 0.407%

    No Known Activations