© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8623
    Prev
    Next
    INDEX
    Explanations

    text in research papers, particularly acknowledgements, disclaimers, mentions of grants, experimental setup, and animal research.

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    :+:
    -0.62
    AddAttribute
    -0.50
    lccn
    -0.50
    PTA
    -0.45
     Wikip
    -0.45
    vP
    -0.44
    ształ
    -0.44
     goodwill
    -0.44
     GLA
    -0.44
    Wik
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.75
    kháu
    0.67
    OGND
    0.65
     للاسماء
    0.59
    opardy
    0.58
     onCancelled
    0.55
    ]--;
    0.55
    存于互联网档案馆
    0.54
    archiviato
    0.53
    complexType
    0.52
    Activations Density 3.614%

    No Known Activations