© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9905
    Prev
    Next
    INDEX
    Explanations

    references to sections and components of formal documents and programs.

    oai_token-act-pair · gemini-2.0-flash

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     section
    -1.20
     phase
    -0.97
     period
    -0.88
     layer
    -0.88
     element
    -0.87
     stage
    -0.85
     category
    -0.82
     sector
    -0.82
     segment
    -0.80
     component
    -0.80
    POSITIVE LOGITS
     EconPapers
    0.68
    Personensuche
    0.67
    routeProvider
    0.67
    contentLoaded
    0.66
    posedge
    0.65
     Squad
    0.65
    AccessorTable
    0.63
    runApp
    0.61
    Class
    0.59
    PEAT
    0.59
    Activations Density 6.002%

    No Known Activations