© 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. 8229
    Prev
    Next
    INDEX
    Explanations

    discussions about payments and debts.

    oai_token-act-pair · gemini-2.0-flash

    terms related to loan payments

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

    Payment

    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
     وتسجيلات
    -0.58
    ⓧ
    -0.57
    UnusedPrivate
    -0.56
     resourceCulture
    -0.53
     Collecting
    -0.50
    /**
    -0.49
     Steal
    -0.49
    רקע
    -0.49
    tou
    -0.48
    WS
    -0.47
    POSITIVE LOGITS
     paid
    1.22
     payment
    1.22
     paying
    1.20
     pay
    1.20
     pays
    1.18
     payments
    1.16
    paid
    1.02
    paying
    1.01
     Paying
    1.00
    payment
    0.99
    Activations Density 1.210%

    No Known Activations