© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    words related to the direction or manner of travel or action

    oai_token-act-pair · gemini-2.0-flash

    route

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     EconPapers
    -0.47
    >--}}
    -0.47
    vidla
    -0.44
     potest
    -0.42
    JsonInclude
    -0.41
    SpringRunner
    -0.40
     󰀄
    -0.40
    ();)
    -0.40
     noDo
    -0.40
    iali
    -0.40
    POSITIVE LOGITS
     route
    2.28
     routes
    1.84
    route
    1.84
     Route
    1.72
     ROUTE
    1.66
    Route
    1.54
    routes
    1.48
     Routes
    1.47
    ROUTE
    1.35
    Routes
    1.33
    Activations Density 1.959%

    No Known Activations