© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4490
    Prev
    Next
    INDEX
    Explanations

    tokens related to travel or transportation

    oai_token-act-pair · gemini-2.0-flash

    Travelling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyCulture
    -0.65
    OGND
    -0.54
     considérons
    -0.54
    __).
    -0.53
     dynamique
    -0.49
     newState
    -0.49
    ього
    -0.48
    ViewFeatures
    -0.47
     solde
    -0.46
     Passenger
    -0.46
    POSITIVE LOGITS
     reaching
    0.96
     reach
    0.96
     reached
    0.91
    reach
    0.86
     reaches
    0.85
     Reach
    0.83
     đến
    0.79
    reached
    0.75
    tothe
    0.71
    Reaching
    0.71
    Activations Density 0.916%

    No Known Activations