© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4588
    Prev
    Next
    INDEX
    Explanations

    instances of paying

    oai_token-act-pair · gemini-2.0-flash

    paid

    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
    Negative Logits
     paid
    -2.80
     pay
    -2.45
     Paid
    -2.31
    paid
    -2.27
     paying
    -2.23
    Paid
    -2.22
     pays
    -2.20
     PAID
    -2.19
     Pay
    -2.17
    Pay
    -2.16
    POSITIVE LOGITS
    RetentionPolicy
    0.63
    hyrchwyd
    0.63
     CreateTagHelper
    0.58
    oa̍t
    0.52
     pinulongan
    0.52
    Hochspringen
    0.50
    FontOfSize
    0.50
    ราะ
    0.50
    numerusform
    0.49
    StackSize
    0.48
    Activations Density 1.666%

    No Known Activations