© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    references to cardinal directions

    oai_token-act-pair · gemini-2.0-flash

    north

    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
    脚注の使い方
    -0.59
    tvguidetime
    -0.54
    निक
    -0.50
    bindValue
    -0.49
     Dubuque
    -0.48
     Guam
    -0.47
     zircon
    -0.47
    readystatechange
    -0.47
     Grosse
    -0.47
     pytest
    -0.46
    POSITIVE LOGITS
     West
    1.53
    West
    1.47
     west
    1.43
     WEST
    1.38
    west
    1.30
    WEST
    1.23
     East
    1.20
    East
    1.16
     east
    1.13
    Western
    1.07
    Activations Density 0.112%

    No Known Activations