© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14654
    Prev
    Next
    INDEX
    Explanations

    acronyms used in NMR spectroscopy and related terms (MHz, linewidth, ppm, lipid, spectra, resonance, P, H, etc.)

    oai_token-act-pair · gemini-2.0-flash

    NMR spectroscopy

    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
    Rüyada
    -0.71
    RTDA
    -0.62
    ViewInit
    -0.61
    Personensuche
    -0.61
    PMailer
    -0.59
     AssemblyCulture
    -0.59
    MigrationBuilder
    -0.57
    SharedDtor
    -0.56
     Accesat
    -0.56
    InstrumentedTest
    -0.55
    POSITIVE LOGITS
    ViewFeatures
    0.64
    CELLANEOUS
    0.57
     DY
    0.55
     HttpHeaders
    0.49
     InputDecoration
    0.47
     contest
    0.45
    Bearbeiten
    0.45
     Bux
    0.44
    undy
    0.44
     Oper
    0.43
    Activations Density 2.756%

    No Known Activations