© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12631
    Prev
    Next
    INDEX
    Explanations

    words related to locations, directions and time, with an emphasis on trails and journeys.

    oai_token-act-pair · gemini-2.0-flash

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     protoimpl
    -0.70
    thâu
    -0.70
    IUrlHelper
    -0.69
    kháu
    -0.69
    expandindo
    -0.68
    AddAttribute
    -0.68
     beginnetje
    -0.66
    setVerticalGroup
    -0.65
     AssemblyCompany
    -0.64
    twimg
    -0.64
    POSITIVE LOGITS
     upwards
    0.57
     up
    0.57
     northward
    0.56
     down
    0.55
     upward
    0.55
     north
    0.55
     rising
    0.53
     raised
    0.52
     nicio
    0.51
     higher
    0.51
    Activations Density 1.211%

    No Known Activations