© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    financial news and discussions of paying for things

    oai_token-act-pair · gemini-2.0-flash

    bill

    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
    Ad
    -0.42
    Game
    -0.40
    munk
    -0.40
    ReusableCell
    -0.40
     '').
    -0.40
     Game
    -0.39
     Schulter
    -0.39
     <<<<<<<<<<<<<<
    -0.39
    msgTypes
    -0.38
     publiés
    -0.38
    POSITIVE LOGITS
     bill
    2.69
    bill
    2.09
     bills
    1.99
     Bill
    1.98
    Bill
    1.87
     BILL
    1.80
    bills
    1.74
    BILL
    1.64
     Bills
    1.61
    Bills
    1.50
    Activations Density 1.124%

    No Known Activations