© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11179
    Prev
    Next
    INDEX
    Explanations

    discussions of exchanging something for something else, especially in a legal or wartime context

    oai_token-act-pair · gemini-2.0-flash

    exchange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    expandindo
    -0.87
    
    -0.85
     Ignorance
    -0.73
    Personensuche
    -0.71
    存于互联网档案馆
    -0.71
     tartalomajánló
    -0.70
     disambiguazione
    -0.70
     propOrder
    -0.68
    öglichkeiten
    -0.67
     diſt
    -0.66
    POSITIVE LOGITS
     reward
    0.77
     pay
    0.74
     rewards
    0.68
     rewarded
    0.65
     award
    0.58
     paid
    0.58
     pays
    0.56
    Reward
    0.56
     Pay
    0.54
    reward
    0.54
    Activations Density 1.164%

    No Known Activations