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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 953
    Prev
    Next
    INDEX
    Explanations

    taxpayer

    np_max-act-logits · gemini-2.0-flash

    language related to finances and government spending

    oai_token-act-pair · gemini-2.0-flash

    taxpayer

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    MENAFN
    -0.89
    ScopeManager
    -0.88
    fjspx
    -0.87
    gonic
    -0.84
     MotionEvent
    -0.83
    \{\\
    -0.78
    tanleria
    -0.77
    AnimationsModule
    -0.77
     himo
    -0.76
    IndentedString
    -0.76
    POSITIVE LOGITS
     taxpayer
    0.75
     taxpayers
    0.73
     tax
    0.61
     Tax
    0.48
     x
    0.47
    Tax
    0.46
    tax
    0.45
     X
    0.43
     tưởng
    0.43
     n
    0.42
    Activations Density 2.005%

    No Known Activations