© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 663
    Prev
    Next
    INDEX
    Explanations

    what appears to be names of people, proteins, places, and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Hid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     experience
    -0.49
     makeStyles
    -0.48
    onViewCreated
    -0.48
    didSet
    -0.48
    rungsseite
    -0.47
     ostavi
    -0.47
     esistono
    -0.47
     kanssa
    -0.47
    ErrorListener
    -0.47
    </i>
    -0.46
    POSITIVE LOGITS
    TypedDataSet
    0.84
    ніципалі
    0.71
    contentLoaded
    0.67
    Ārējās
    0.67
    GeneratedCode
    0.67
    ientôt
    0.66
    Liefs
    0.65
     dõi
    0.64
     архивлан
    0.64
    #
    0.62
    Activations Density 6.439%

    No Known Activations