© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12291
    Prev
    Next
    INDEX
    Explanations

    phrases interspersed with metadata, especially song lyrics written in French

    oai_token-act-pair · gemini-2.0-flash

    Opera/Repeated Phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.53
    ollectionView
    -0.49
    emph
    -0.48
     betweenstory
    -0.47
     sessionFactory
    -0.46
    THON
    -0.45
    androidx
    -0.45
    ecka
    -0.44
    ress
    -0.43
     Prior
    -0.43
    POSITIVE LOGITS
    Билгалдахарш
    0.74
     AssemblyTitle
    0.62
    UnknownFieldSet
    0.60
     يتيمه
    0.56
     utafitiHapana
    0.55
     kasarigan
    0.54
    WebVitals
    0.54
    DockStyle
    0.54
     initComponents
    0.54
    vician
    0.54
    Activations Density 1.783%

    No Known Activations