© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4876
    Prev
    Next
    INDEX
    Explanations

    words or word parts ending in "um" or "us."

    oai_token-act-pair · gemini-2.0-flash

    um

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    um
    -2.64
    UM
    -2.16
    ums
    -1.73
     um
    -1.56
    Um
    -1.45
     Um
    -1.37
    umm
    -1.31
    UMS
    -1.30
    umt
    -1.29
    umn
    -1.17
    POSITIVE LOGITS
    ThroughAttribute
    0.75
    SupportActionBar
    0.69
    بوابة
    0.67
    parsedMessage
    0.66
    yargs
    0.66
     المعيارى
    0.66
    orianCalendar
    0.65
    AccessFile
    0.64
     getItemCount
    0.64
     링크
    0.64
    Activations Density 1.900%

    No Known Activations