© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1555
    Prev
    Next
    INDEX
    Explanations

    positive reviews and descriptions of visual media and design, especially if professional or high-quality.

    oai_token-act-pair · gemini-2.0-flash

    visual media and quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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>
    -0.51
     '/':
    -0.50
     porridge
    -0.50
    modium
    -0.46
    Przypisy
    -0.46
     cargo
    -0.45
    浪
    -0.45
    ьа
    -0.44
    はじめに
    -0.44
    اں
    -0.42
    POSITIVE LOGITS
    XmlAccessType
    0.82
    setVerticalGroup
    0.77
    DockStyle
    0.76
    IonicModule
    0.74
    PreferredItem
    0.71
    addCriterion
    0.71
    makeConstraints
    0.68
    RectangleBorder
    0.68
    AnchorStyles
    0.66
     ExecuteAsync
    0.64
    Activations Density 1.450%

    No Known Activations