© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5500
    Prev
    Next
    INDEX
    Explanations

    the words "funds" and "InstanceState", suggesting it looks for the availability or persistency of resources

    oai_token-act-pair · gemini-2.0-flash

    coding or legal/financial

    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
     chré
    -0.69
     kár
    -0.68
    InstanceState
    -0.67
     eléctricas
    -0.66
     dépos
    -0.66
     kasarigan
    -0.63
    GNUC
    -0.62
    يكب
    -0.62
     mulus
    -0.61
     comigo
    -0.60
    POSITIVE LOGITS
     result
    0.61
    QRST
    0.60
    IBAction
    0.58
     noDo
    0.57
     rate
    0.57
    initComponents
    0.57
    PMailer
    0.56
    Przypisy
    0.56
     a
    0.54
    حال
    0.53
    Activations Density 1.016%

    No Known Activations