© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14145
    Prev
    Next
    INDEX
    Explanations

    words used in business, especially in investment banking, and often appears near "and"

    oai_token-act-pair · gemini-2.0-flash

    terms related to mergers and acquisitions

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

    Mergers and Acquisitions

    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
     poto
    -0.51
     дописавши
    -0.50
     Forgotten
    -0.49
    opla
    -0.48
     gawas
    -0.48
     schild
    -0.48
     SPRINGS
    -0.47
     Natsu
    -0.46
     nick
    -0.45
     Springs
    -0.45
    POSITIVE LOGITS
     deal
    1.02
     acquisitions
    0.90
     acquisition
    0.89
     deals
    0.86
     M
    0.86
     merger
    0.83
     Mer
    0.81
     acquis
    0.81
    deal
    0.81
     Acquisition
    0.79
    Activations Density 1.628%

    No Known Activations