© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    words that are both related to regulations/entitlements and physical/vehicular safety

    oai_token-act-pair · gemini-2.0-flash

    travel

    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
     driver
    -0.90
     drivers
    -0.90
    CppMethod
    -0.88
     Driver
    -0.88
    driver
    -0.84
     Drivers
    -0.84
    Driver
    -0.83
    Drivers
    -0.82
     unknownFields
    -0.81
     whoſe
    -0.79
    POSITIVE LOGITS
     travel
    1.25
     travelling
    1.24
     traveling
    1.19
    Travelling
    1.12
    travel
    1.07
     travelled
    1.07
     Travelling
    1.04
     travels
    1.02
     Traveling
    1.00
     traveled
    0.99
    Activations Density 2.887%

    No Known Activations