© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11491
    Prev
    Next
    INDEX
    Explanations

    text related to loan applications

    oai_token-act-pair · gemini-2.0-flash

    loan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -2.17
     Loan
    -2.00
     loans
    -1.93
     lending
    -1.92
    Loan
    -1.86
     LOAN
    -1.85
    loan
    -1.84
     Lending
    -1.83
     Loans
    -1.82
     lent
    -1.68
    POSITIVE LOGITS
    Przypisy
    0.52
    GenerationType
    0.50
    getItemId
    0.46
    Viitteet
    0.43
     bag
    0.43
    zarchiwizowane
    0.42
     Bag
    0.42
     Dương
    0.41
     jár
    0.40
    ség
    0.40
    Activations Density 2.140%

    No Known Activations