© 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. 1623
    Prev
    Next
    INDEX
    Explanations

    sentence fragments involving composition or structure using words like "of", "bit", "up", or "with".

    oai_token-act-pair · gemini-2.0-flash

    composed of

    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
     ویکی‌پدی
    -0.72
    LookAnd
    -0.59
    contentLoaded
    -0.55
    WebServlet
    -0.55
    TintMode
    -0.54
    олові
    -0.54
     jLabel
    -0.54
    ')));
    -0.53
    PreferredItem
    -0.53
    typeDefinition
    -0.53
    POSITIVE LOGITS
     comprised
    0.65
     consisting
    0.63
     composed
    0.58
     consisted
    0.58
     consists
    0.57
     comprising
    0.53
     comprises
    0.50
     consist
    0.48
     terdiri
    0.47
    Vidite
    0.47
    Activations Density 2.821%

    No Known Activations