© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3275
    Prev
    Next
    INDEX
    Explanations

    terms used in scientific articles, especially related to medicine and chemistry.

    oai_token-act-pair · gemini-2.0-flash

    scientific/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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     EconPapers
    -0.68
     Drapeau
    -0.65
    neté
    -0.64
    addGap
    -0.61
    RegistryLite
    -0.59
    ьаж
    -0.58
    wohner
    -0.58
     snippetHide
    -0.58
     ApiException
    -0.57
     Obrador
    -0.57
    POSITIVE LOGITS
     deterrent
    0.48
    Personendaten
    0.46
    terase
    0.45
     matching
    0.44
    Portale
    0.44
    pensione
    0.44
     deterrence
    0.44
    hingga
    0.43
     weighted
    0.43
    DATABASES
    0.43
    Activations Density 4.419%

    No Known Activations