© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5013
    Prev
    Next
    INDEX
    Explanations

    passages about coal-powered locomotives

    oai_token-act-pair · gemini-2.0-flash

    coal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rubin
    -0.57
    SpringRunner
    -0.52
    perror
    -0.51
    ద్య
    -0.48
     bronze
    -0.48
    ילום
    -0.47
    ラク
    -0.46
     Bronze
    -0.46
     solder
    -0.45
    )))
    -0.45
    POSITIVE LOGITS
     Paglinawan
    0.92
    +#+#
    0.89
    makeConstraints
    0.73
     للمعارف
    0.72
    LookAnd
    0.69
    InvalidProtocol
    0.65
     AssemblyCulture
    0.65
     transfieras
    0.63
    SpringBootTest
    0.61
     seam
    0.61
    Activations Density 0.859%

    No Known Activations