© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13738
    Prev
    Next
    INDEX
    Explanations

    words related to beltways or highways, especially their geographic location

    oai_token-act-pair · gemini-2.0-flash

    terms related to encircling or surrounding

    np_token-act-pair-logits · gpt-4o-mini

    circular shapes and motion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ########.
    -0.67
    
    -0.62
    RegressionTest
    -0.54
    XmlEnum
    -0.52
    abestanden
    -0.50
    bigsqcup
    -0.50
     DBNull
    -0.49
    はじめに
    -0.49
     referenties
    -0.49
     ostavi
    -0.49
    POSITIVE LOGITS
     around
    1.62
    around
    1.52
     Around
    1.46
    Around
    1.44
     AROUND
    1.35
    AROUND
    1.34
     surrounding
    1.31
     alrededor
    1.27
     round
    1.23
     surrounds
    1.20
    Activations Density 1.851%

    No Known Activations