© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5230
    Prev
    Next
    INDEX
    Explanations

    the word "office" and its different forms

    oai_token-act-pair · gemini-2.0-flash

    references to an "office."

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

    office

    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
     resourceCulture
    -0.71
     виправивши
    -0.62
    Personensuche
    -0.62
     defStyleAttr
    -0.57
    ngdoc
    -0.55
    bcryptjs
    -0.54
     Roskov
    -0.54
     ویکی‌پدی
    -0.53
    Datuak
    -0.52
     otomatig
    -0.51
    POSITIVE LOGITS
    큼
    0.56
     juri
    0.51
    newBuilder
    0.50
     Jeb
    0.48
     IMPLIED
    0.48
     torne
    0.48
     boule
    0.48
    DoubleQuotes
    0.48
    pernicus
    0.47
    ุ่น
    0.47
    Activations Density 1.047%

    No Known Activations