© 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. 2094
    Prev
    Next
    INDEX
    Explanations

    financial news, focusing on company names, stock tickers, and financial results

    oai_token-act-pair · gemini-2.0-flash

    company

    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
    })();
    -0.91
    Demografie
    -0.89
     Efq
    -0.89
     purpoſe
    -0.86
     Monfieur
    -0.80
    AddTagHelper
    -0.79
     itſelf
    -0.78
     Majefty
    -0.77
     obfer
    -0.77
     himſelf
    -0.77
    POSITIVE LOGITS
    lo
    0.41
     ra
    0.35
    lag
    0.34
    windowFixed
    0.34
     recruited
    0.33
     z
    0.33
    rom
    0.32
    tag
    0.32
    param
    0.31
    取
    0.31
    Activations Density 1.609%

    No Known Activations