© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6488
    Prev
    Next
    INDEX
    Explanations

    words related to viewpoints, officialdom, research, opinions, and information.

    oai_token-act-pair · gemini-2.0-flash

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.77
     many
    -0.72
     under
    -0.67
     only
    -0.65
     just
    -0.65
     be
    -0.61
     are
    -0.60
     up
    -0.59
     in
    -0.59
     its
    -0.59
    POSITIVE LOGITS
    writeFieldEnd
    0.92
    Tembelea
    0.89
     Administrativna
    0.88
    endphp
    0.86
     nonatomic
    0.82
    UserScript
    0.81
    IntoConstraints
    0.78
    ंदीखरीदारी
    0.78
     rhestr
    0.78
     Мексичка
    0.77
    Activations Density 20.517%

    No Known Activations