© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15475
    Prev
    Next
    INDEX
    Explanations

    language related to financial difficulties, specifically taxes, debt, and insolvency.

    oai_token-act-pair · gemini-2.0-flash

    Legal and financial issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PageRoute
    -0.53
    ADEL
    -0.46
    ByPrimaryKey
    -0.46
    copyWith
    -0.45
     समीक्षक
    -0.44
    CUT
    -0.44
     Schles
    -0.43
    antin
    -0.43
     coper
    -0.42
    anterie
    -0.42
    POSITIVE LOGITS
    kháu
    0.68
    期刊论文
    0.67
     >=",
    0.65
    انيف
    0.65
     jScrollPane
    0.58
     onOptions
    0.58
     وتسجيلات
    0.57
    Tazama
    0.56
    tvguidetime
    0.54
     @}
    0.54
    Activations Density 3.437%

    No Known Activations