© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11979
    Prev
    Next
    INDEX
    Explanations

    mentions of actions involving money, along with words like "that", "the", "to", and "be" which may be related to phrasal structure

    oai_token-act-pair · gemini-2.0-flash

    pay

    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
     paid
    -1.93
     Paid
    -1.73
     pay
    -1.73
     paying
    -1.70
    paid
    -1.60
     Paying
    -1.58
     payed
    -1.57
    Paid
    -1.56
     PAID
    -1.55
    paying
    -1.52
    POSITIVE LOGITS
    ReusableCell
    0.70
    WriteTagHelper
    0.70
    ]")]
    0.69
    出版年
    0.69
    ]--;
    0.64
    felves
    0.64
     calendriers
    0.59
     createState
    0.59
    TagHelper
    0.58
     onCancelled
    0.56
    Activations Density 0.958%

    No Known Activations