© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6542
    Prev
    Next
    INDEX
    Explanations

    travel-related words

    oai_token-act-pair · gemini-2.0-flash

    Booking/Reservations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    lossary
    -0.43
    reportWebVitals
    -0.43
    assertj
    -0.40
    RestTemplate
    -0.40
     intervi
    -0.39
     geri
    -0.39
     (!_
    -0.39
     /(\
    -0.39
    CopyWith
    -0.38
    JAXB
    -0.38
    POSITIVE LOGITS
    ViewFeatures
    0.82
     Booking
    0.78
     Reservation
    0.71
    脚注の使い方
    0.70
    Décès
    0.70
     bookings
    0.69
     reservation
    0.68
     booking
    0.68
     reservations
    0.66
    Booking
    0.66
    Activations Density 0.642%

    No Known Activations