© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2233
    Prev
    Next
    INDEX
    Explanations

    language related to finance and the stock market, particularly losses

    oai_token-act-pair · gemini-2.0-flash

    finance and economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    URLException
    -0.65
    UrlResolution
    -0.59
     становника
    -0.54
     Keuangan
    -0.52
     mergeFrom
    -0.52
    MemoryWarning
    -0.52
     viewDidLoad
    -0.52
     postIndex
    -0.51
     TestBed
    -0.50
    #+#
    -0.50
    POSITIVE LOGITS
     getCode
    0.51
     SAH
    0.49
    sią
    0.49
     shingles
    0.47
     crowns
    0.47
     turban
    0.47
     strateg
    0.46
    헌
    0.45
     globes
    0.44
     manna
    0.44
    Activations Density 9.033%

    No Known Activations