© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4058
    Prev
    Next
    INDEX
    Explanations

    content related to tax regulations and legal contexts

    oai_token-act-pair · gemini-2.0-flash

    tokens representing specific tax-related terminologies

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

    Taxes

    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
    

    -0.38
     Sou
    -0.37
    ディア
    -0.36
    emit
    -0.35
     carnet
    -0.35
    enger
    -0.34
    Sou
    -0.34
    ↵
    -0.34
     writer
    -0.33
    stant
    -0.32
    POSITIVE LOGITS
    ########.
    1.01
     مشين
    0.91
     <>",
    0.85
     שוליים
    0.82
     myſelf
    0.80
     betweenstory
    0.77
    ніципалі
    0.75
    ^(@)
    0.75
     "..\..\..\
    0.71
    цезда
    0.70
    Activations Density 1.346%

    No Known Activations