© 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. 12741
    Prev
    Next
    INDEX
    Explanations

    a mix of punctuation and named entities

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    .)}
    -0.53
    expandindo
    -0.52
    。</
    -0.52
    Datuak
    -0.50
    PhysRev
    -0.49
    )}
    -0.48
    hloromethane
    -0.48
    )}>
    -0.46
    zerland
    -0.45
    。】
    -0.45
    POSITIVE LOGITS
    ''
    0.95
    ""
    0.91
     ”
    0.82
    ”
    0.81
    」
    0.79
     AssemblyCulture
    0.75
    ’’
    0.73
    ″
    0.72
    "[
    0.69
    »
    0.68
    Activations Density 1.338%

    No Known Activations