© 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. 11044
    Prev
    Next
    INDEX
    Explanations

    HTML formatting tags for making text bold or italic

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    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
     EconPapers
    -1.76
    AddTagHelper
    -1.62
    setVerticalGroup
    -1.53
     propOrder
    -1.52
    InjectAttribute
    -1.51
     CreateTagHelper
    -1.50
    sizeCache
    -1.48
    parsedMessage
    -1.48
    ViewImports
    -1.48
    oredCriteria
    -1.47
    POSITIVE LOGITS
    '
    1.00
    k
    0.89
    v
    0.88
    m
    0.87
    c
    0.86
    t
    0.84
    b
    0.83
    p
    0.82
    n
    0.81
    s
    0.81
    Activations Density 0.088%

    No Known Activations