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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12756
    Prev
    Next
    INDEX
    Explanations

    a mix of information related to Volkswagen cars, database programming syntax, trapping rodents, and car reviews; it's impossible to give a more specific single sentence summary

    oai_token-act-pair · gemini-2.0-flash

    Volkswagen cars

    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
     Normdatei
    -0.72
    NameInMap
    -0.70
    MigrationBuilder
    -0.69
     hObject
    -0.69
     utafiti
    -0.67
    SequentialGroup
    -0.67
     esternos
    -0.65
    Bronnen
    -0.62
    MessageState
    -0.61
    UnsafeEnabled
    -0.61
    POSITIVE LOGITS
     entière
    0.53
    dat
    0.52
     ugu
    0.49
    idge
    0.47
     BeautifulSoup
    0.47
     restart
    0.46
    SourceChecksum
    0.45
    ఔ
    0.45
     restarting
    0.45
     restarted
    0.43
    Activations Density 0.773%

    No Known Activations