© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11740
    Prev
    Next
    INDEX
    Explanations

    a mix of financial news, quantum computing and football

    oai_token-act-pair · gemini-2.0-flash

    race

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    complexContent
    -0.69
     cheminée
    -0.52
    SpringBootTest
    -0.50
     تانيه
    -0.48
     pinulongan
    -0.47
    setPixel
    -0.47
     Hick
    -0.45
    ուն
    -0.43
    liceerd
    -0.43
    etsk
    -0.42
    POSITIVE LOGITS
     race
    3.42
    race
    2.88
     Race
    2.84
    Race
    2.78
     RACE
    2.50
     races
    2.48
    RACE
    2.28
     raced
    2.13
     Races
    2.13
    races
    1.98
    Activations Density 2.458%

    No Known Activations