© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7964
    Prev
    Next
    INDEX
    Explanations

    the word "seal" and related words like "sealing" in contexts related to physical barriers or closures, and sometimes also the word "draw."

    oai_token-act-pair · gemini-2.0-flash

    seal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    StoryboardSegue
    -1.57
     Мексичка
    -1.52
     ")");
    -1.45
     contextLoads
    -1.43
    EDEFAULT
    -1.40
     estekak
    -1.37
     ब्रेकडाउन
    -1.34
    __':
    -1.33
     tartalomajánló
    -1.33
    Tembelea
    -1.30
    POSITIVE LOGITS
    .
    1.16
    ,
    1.10
    (
    1.05
     
    1.05
    er
    0.96
     "
    0.91
     “
    0.90
    /
    0.87
    o
    0.85
    ↵
    0.84
    Activations Density 3.624%

    No Known Activations