© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8850
    Prev
    Next
    INDEX
    Explanations

    mentions of credit reports and credit reporting agencies

    oai_token-act-pair · gemini-2.0-flash

    credit report-related terms

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

    reporting

    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
    ècie
    -0.69
    HandlerContext
    -0.51
    Aiheesta
    -0.48
     igr
    -0.47
     impro
    -0.47
    FileChooser
    -0.46
    IsContent
    -0.46
    ValueGeneration
    -0.45
    __);
    -0.44
    karten
    -0.43
    POSITIVE LOGITS
     reporting
    0.71
    reporting
    0.66
    report
    0.63
     Taktlose
    0.60
     report
    0.60
    exper
    0.59
     Reporting
    0.59
    Collection
    0.58
     REPORTING
    0.57
    Report
    0.57
    Activations Density 1.714%

    No Known Activations