© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1860
    Prev
    Next
    INDEX
    Explanations

    financial information and companies

    oai_token-act-pair · gemini-2.0-flash

    financial advisor-related terms

    np_token-act-pair-logits · gpt-4o-mini

    Financial planning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     premium
    -0.99
    premium
    -0.89
     Premium
    -0.81
    Premium
    -0.77
     PREMIUM
    -0.75
     premiums
    -0.73
    PREMI
    -0.66
     PREMI
    -0.64
     contributions
    -0.62
     Premi
    -0.62
    POSITIVE LOGITS
     Planner
    0.85
     Financial
    0.83
     financial
    0.82
     planner
    0.81
    Financial
    0.80
    Planner
    0.80
     FINANCIAL
    0.79
     Planners
    0.75
     planners
    0.75
    financial
    0.75
    Activations Density 1.591%

    No Known Activations