© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3733
    Prev
    Next
    INDEX
    Explanations

    words that are used to describe auto racing

    oai_token-act-pair · gemini-2.0-flash

    Motorsports and competition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ball
    -1.22
     balls
    -1.15
    balls
    -1.14
    Ball
    -1.12
     Ball
    -1.09
    ball
    -1.08
     Balls
    -1.06
     BALL
    -1.05
    BALL
    -1.04
    Balls
    -1.00
    POSITIVE LOGITS
     Print
    0.36
    correre
    0.36
    regional
    0.34
    Prints
    0.34
     Regional
    0.34
    Regional
    0.34
     M
    0.33
    MODIFY
    0.33
     regional
    0.33
    Lieutenant
    0.32
    Activations Density 0.389%

    No Known Activations