© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7653
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and financial topics

    oai_token-act-pair · gemini-2.0-flash

    loans and banking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     kaynağından
    -0.48
     Aula
    -0.47
    ----</
    -0.46
    webElementXpaths
    -0.45
    ('.'
    -0.44
    DeleteBehavior
    -0.44
     Nielsen
    -0.44
    kå
    -0.42
    elekt
    -0.42
     Majestic
    -0.41
    POSITIVE LOGITS
     loan
    0.77
     banks
    0.75
     lending
    0.74
     banking
    0.73
    matchCondition
    0.72
     loans
    0.72
    Banks
    0.70
     LOAN
    0.69
     Loans
    0.68
     Loan
    0.68
    Activations Density 0.869%

    No Known Activations