© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11306
    Prev
    Next
    INDEX
    Explanations

    the word "South" or "Southern" in various contexts, sometimes with a slight preference for geographic locations or place names

    oai_token-act-pair · gemini-2.0-flash

    South

    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
     South
    -2.33
    South
    -2.16
     south
    -1.82
     SOUTH
    -1.82
    south
    -1.77
    SOUTH
    -1.67
     North
    -1.26
    North
    -1.16
     north
    -1.14
    南
    -1.05
    POSITIVE LOGITS
    WaitGroup
    0.79
    amental
    0.68
    脚注の使い方
    0.67
     Godt
    0.65
     initComponents
    0.65
    __()
    0.64
    hush
    0.64
     autant
    0.64
    ReusableCell
    0.63
    welfare
    0.62
    Activations Density 4.273%

    No Known Activations