© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10425
    Prev
    Next
    INDEX
    Explanations

    cardinal directions and related terms

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     West
    -1.91
     west
    -1.84
    West
    -1.79
     WEST
    -1.66
    west
    -1.63
     East
    -1.59
     east
    -1.55
    East
    -1.52
    WEST
    -1.52
     North
    -1.50
    POSITIVE LOGITS
    脚注の使い方
    0.80
    tvguidetime
    0.62
     propOrder
    0.61
     Lithuanian
    0.54
     Cambodian
    0.54
     Guam
    0.53
     Grosse
    0.52
    tanooga
    0.52
     Dubuque
    0.52
     Fiji
    0.52
    Activations Density 0.136%

    No Known Activations