© 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. 8448
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting, especially those indicating titles, links, and code

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    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
    <bos>
    -2.31
    ↵↵
    -1.08
    GEBURTSDATUM
    -0.91
     '\\;'
    -0.86
    UnusedPrivate
    -0.79
     архивлан
    -0.79
    SourceChecksum
    -0.79
    '
    -0.74
    DockStyle
    -0.74
    '});
    -0.71
    POSITIVE LOGITS
    <strong>
    0.68
    <b>
    0.52
    確認ください
    0.48
    INGEN
    0.47
     total
    0.47
     far
    0.46
    iname
    0.46
     DialogInterface
    0.46
    asch
    0.46
     déjà
    0.45
    Activations Density 2.004%

    No Known Activations