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. 16215
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Department," often followed by "of"

    oai_token-act-pair · gemini-2.0-flash

    Department

    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
    DockStyle
    -0.97
    GenerationType
    -0.86
     مشين
    -0.85
     otomatig
    -0.79
    };*/
    -0.77
    sizeCache
    -0.73
    protoimpl
    -0.73
     <=",
    -0.71
     postIndex
    -0.71
     ddelweddau
    -0.71
    POSITIVE LOGITS
    blij
    0.45
     Bupati
    0.38
    8
    0.38
    #
    0.38
    stateProvider
    0.37
     i
    0.36
    7
    0.36
    ~
    0.36
    getMock
    0.36
    tailed
    0.36
    Activations Density 3.886%

    No Known Activations