© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4659
    Prev
    Next
    INDEX
    Explanations

    technical language related to superconductivity and electron interactions

    oai_token-act-pair · gemini-2.0-flash

    Scientific, physics concepts

    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
     AspNetCore
    -0.72
    [--
    -0.69
    }")]
    -0.63
     pitié
    -0.63
     commerciaux
    -0.60
     commerciali
    -0.59
    ITHUB
    -0.58
    TestTools
    -0.57
    ']],
    -0.57
     gangen
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.57
     HttpServlet
    0.57
    CppCodeGen
    0.52
    SerializedName
    0.52
    Sucesor
    0.52
    WebElementEntity
    0.51
     NSCoder
    0.47
     s
    0.47
    Seeder
    0.46
     noqa
    0.44
    Activations Density 2.288%

    No Known Activations