© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    financial data in the form of years and monetary amounts

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to business and finance

    np_token-act-pair-logits · gpt-4o-mini

    Revenue and finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.54
     насељу
    -0.47
    CGRectMake
    -0.38
    tonsoft
    -0.38
     näm
    -0.38
    cov
    -0.37
     estekak
    -0.37
    vitis
    -0.36
    новниш
    -0.36
    丰富的
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.76
     CreateTagHelper
    0.73
    sizeCache
    0.66
     Normdatei
    0.66
     IBOutlet
    0.65
    sells
    0.65
     revenue
    0.64
     concerto
    0.63
     BrowserModule
    0.60
     jScrollPane
    0.59
    Activations Density 1.689%

    No Known Activations