© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5987
    Prev
    Next
    INDEX
    Explanations

    documents about loans, finances, and policies

    oai_token-act-pair · gemini-2.0-flash

    Loans and monetary topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     loan
    -2.09
     Loan
    -1.95
     loans
    -1.88
    Loan
    -1.85
     borrower
    -1.84
     borrowers
    -1.84
     borrow
    -1.84
     Loans
    -1.83
     borrowing
    -1.80
    Borrow
    -1.80
    POSITIVE LOGITS
     =
    0.85
    /*
    0.49
    culada
    0.47
     PMS
    0.46
    l
    0.45
     Económica
    0.44
    Académie
    0.44
    sior
    0.43
     $=$
    0.43
     Edelman
    0.42
    Activations Density 1.481%

    No Known Activations