© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12877
    Prev
    Next
    INDEX
    Explanations

    cardinal directions and the context they're used in

    oai_token-act-pair · gemini-2.0-flash

    west

    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
    -0.61
     Joplin
    -0.57
    tvguidetime
    -0.54
    Rüyada
    -0.54
     Fiji
    -0.50
     Ugandan
    -0.50
    kuuta
    -0.50
     Topeka
    -0.50
     Sardin
    -0.49
    üyada
    -0.49
    POSITIVE LOGITS
    North
    1.12
     North
    1.09
    north
    1.04
     NORTH
    1.02
     north
    1.00
    NORTH
    0.96
    北
    0.88
    northern
    0.85
     south
    0.84
    Northern
    0.84
    Activations Density 0.273%

    No Known Activations