© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12637
    Prev
    Next
    INDEX
    Explanations

    sentences about people and money

    oai_token-act-pair · gemini-2.0-flash

    Money and payments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     funds
    -0.84
     payments
    -0.78
     money
    -0.78
     payment
    -0.78
     Funds
    -0.75
    rungsseite
    -0.68
     Payments
    -0.68
     Uang
    -0.68
     fund
    -0.67
     pagamento
    -0.66
    POSITIVE LOGITS
     parting
    0.63
     handing
    0.62
    tinyos
    0.60
    انيف
    0.59
     handed
    0.58
    findpost
    0.54
     betweenstory
    0.52
     pon
    0.51
     contribute
    0.50
     contributed
    0.50
    Activations Density 1.043%

    No Known Activations