© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    text about Volkswagen vehicles and their recalls, particularly in relation to DSG transmissions and issues in the United States and China.

    oai_token-act-pair · gemini-2.0-flash

    recall

    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
     Baillargeon
    -0.54
     himſelf
    -0.52
    olyb
    -0.50
    rennen
    -0.48
     strip
    -0.48
     Offisielt
    -0.47
     terbentuk
    -0.47
     strips
    -0.46
     Cosa
    -0.45
    isContained
    -0.45
    POSITIVE LOGITS
     recall
    1.72
     recalled
    1.58
     recalls
    1.52
     recalling
    1.47
    recall
    1.45
     Recall
    1.37
    Recall
    1.30
     recollect
    1.05
     Rec
    1.05
     recollection
    0.92
    Activations Density 0.683%

    No Known Activations