Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9527
    Prev
    Next
    INDEX
    Explanations

    mentions of taxes and tax-related legislation

    oai_token-act-pair · gemini-2.0-flash

    tax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     tax
    -1.44
     Tax
    -1.32
    Tax
    -1.28
    tax
    -1.27
     TAX
    -1.20
    TAX
    -1.06
     taxed
    -0.86
     taxable
    -0.76
     taxation
    -0.73
    税
    -0.73
    POSITIVE LOGITS
    CPtr
    0.78
    principalColumn
    0.69
     CURIAM
    0.69
    CodeAttribute
    0.68
    awtextra
    0.63
     Audiodateien
    0.59
    RegressionTest
    0.58
    rungsseite
    0.58
    Autoritní
    0.57
     AssemblyTitle
    0.56
    Activations Density 2.825%

    No Known Activations