© 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. 15713
    Prev
    Next
    INDEX
    Explanations

    language describing the parsing, subdividing, or breaking down of abstract or concrete concepts.

    oai_token-act-pair · gemini-2.0-flash

    break, broken

    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
    Према
    -0.65
    المناصب
    -0.55
    awtextra
    -0.55
     AssemblyTitle
    -0.50
    Aholisi
    -0.46
    StandardCharsets
    -0.45
     समीक्षक
    -0.45
     refusé
    -0.45
     Hivatalos
    -0.45
    Сере
    -0.43
    POSITIVE LOGITS
     break
    2.91
     breaking
    2.61
    break
    2.59
     Break
    2.59
     breaks
    2.58
     broken
    2.55
     broke
    2.47
    Break
    2.45
     BREAK
    2.41
     Breaking
    2.34
    Activations Density 2.076%

    No Known Activations