© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5006
    Prev
    Next
    INDEX
    Explanations

    initialisms, abbreviations, and acronyms in medical or scientific documents

    oai_token-act-pair · gemini-2.0-flash

    Numbers one, two

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    yntaxException
    -0.69
    rungsseite
    -0.63
    ArgsConstructor
    -0.60
    WebServlet
    -0.60
     gué
    -0.57
    ">//
    -0.57
     Púb
    -0.55
     GlobalKey
    -0.55
    Referencie
    -0.54
     Савез
    -0.53
    POSITIVE LOGITS
     One
    2.58
    One
    2.27
     ONE
    1.89
    ONE
    1.52
     Ones
    1.29
     Two
    1.03
    one
    0.94
     onep
    0.92
    Two
    0.91
     Three
    0.90
    Activations Density 13.977%

    No Known Activations