© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5115
    Prev
    Next
    INDEX
    Explanations

    mentions of negotiations, agreements, or business deals.

    oai_token-act-pair · gemini-2.0-flash

    business deals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     deal
    -3.08
     Deal
    -3.00
    Deal
    -2.98
    deal
    -2.95
     deals
    -2.94
     dealt
    -2.75
     DEAL
    -2.73
     Deals
    -2.66
    Deals
    -2.52
     dealing
    -2.48
    POSITIVE LOGITS
    adaptiveStyles
    0.51
    Personendaten
    0.50
    SocketChannel
    0.49
    varnothing
    0.49
     avond
    0.46
    ouro
    0.46
     direzione
    0.46
    ivore
    0.46
    tomcat
    0.45
     McGee
    0.45
    Activations Density 1.639%

    No Known Activations