© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    technical jargon and statistical terms in medical, legal and scientific texts.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical text

    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
     Theſe
    -0.73
     himſelf
    -0.72
     plais
    -0.72
     Mga
    -0.71
     Monfieur
    -0.69
     theſe
    -0.66
     dieux
    -0.65
     traités
    -0.65
     myſelf
    -0.64
     againſt
    -0.64
    POSITIVE LOGITS
    Rhestr
    0.72
    Према
    0.63
     AssemblyCompany
    0.63
    windowFixed
    0.58
    hysema
    0.56
    Demografía
    0.55
     AssemblyCulture
    0.55
     disambiguazione
    0.54
     motors
    0.51
    BeginContext
    0.51
    Activations Density 6.678%

    No Known Activations