© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10066
    Prev
    Next
    INDEX
    Explanations

    terms related to medical, scientific, and chemical nomenclature

    oai_token-act-pair · gemini-2.0-flash

    scientific and medical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    IndentedString
    -0.48
    \}^{
    -0.47
    はじめに
    -0.46
     tir
    -0.45
     continúas
    -0.45
    })`
    -0.45
    ại
    -0.45
     extra
    -0.44
     hant
    -0.44
    featureID
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.73
     Monfieur
    0.69
     pleaſure
    0.69
    ErrUnexpectedEOF
    0.68
     Theſe
    0.62
     autorytatywna
    0.61
     houſe
    0.61
     дописавши
    0.60
     صوتيه
    0.58
     dedans
    0.57
    Activations Density 3.307%

    No Known Activations