© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13764
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially company names with "Sew", "Easy", "Creative" and "Lite" included.

    oai_token-act-pair · gemini-2.0-flash

    Product/business names

    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
     otomatig
    -0.65
     informée
    -0.60
    RegressionTest
    -0.59
    Rhestr
    -0.58
    AsUp
    -0.58
    érape
    -0.56
     estekak
    -0.55
    +#+#
    -0.54
    setupUi
    -0.54
    UrlResolution
    -0.53
    POSITIVE LOGITS
     FontWeight
    0.52
    mergeFrom
    0.52
    ViewImports
    0.51
    getColumnIndex
    0.50
    OURCE
    0.49
    stands
    0.48
    ftagPool
    0.48
     setempat
    0.48
    äld
    0.47
     oreille
    0.47
    Activations Density 2.908%

    No Known Activations