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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14821
    Prev
    Next
    INDEX
    Explanations

    words that describe politics economics or science in the context of an argument

    oai_token-act-pair · gemini-2.0-flash

    code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     stuff
    -1.30
     legislation
    -1.13
     information
    -1.09
     evidence
    -1.08
     equipment
    -1.02
     advice
    -0.96
    stuff
    -0.95
     footage
    -0.93
    legislation
    -0.92
     Stuff
    -0.91
    POSITIVE LOGITS
    GraphicsUnit
    0.99
     CreateTagHelper
    0.85
    TagMode
    0.85
     يتيمه
    0.78
    出版年
    0.74
    RegressionTest
    0.73
     ISNI
    0.70
     mergeFrom
    0.69
    MemoryWarning
    0.68
    Autoritní
    0.68
    Activations Density 3.181%

    No Known Activations