© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12450
    Prev
    Next
    INDEX
    Explanations

    language related to business financials and accounting

    oai_token-act-pair · gemini-2.0-flash

    finance/accounting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     whoſe
    -0.85
     Efq
    -0.84
     myſelf
    -0.83
     Theſe
    -0.82
    */;
    -0.81
     ―――――
    -0.80
     Reſ
    -0.75
     Conſ
    -0.75
     itſelf
    -0.74
     Diſ
    -0.72
    POSITIVE LOGITS
    حياته
    0.50
    oader
    0.48
     NUKAT
    0.47
    ScrollBar
    0.47
     szóci
    0.43
     teoria
    0.43
    !("{
    0.41
     meilleure
    0.41
     meilleurs
    0.41
    <>("
    0.40
    Activations Density 2.132%

    No Known Activations