© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12300
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings involving damage and injury

    oai_token-act-pair · gemini-2.0-flash

    coding-related terms and tags

    np_token-act-pair-logits · gpt-4o-mini

    Damages and harm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    findpost
    -0.60
    insee
    -0.51
     refs
    -0.49
     officielles
    -0.44
    PhysRevD
    -0.44
    쿵
    -0.43
     algoritmo
    -0.43
    piram
    -0.43
    帖最后由
    -0.43
     hyvä
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.75
     autorytatywna
    0.66
    NameInMap
    0.66
    IBarButtonItem
    0.66
     kasarigan
    0.63
    ."],
    0.60
    :✨
    0.60
    SerializedSize
    0.58
    出版年
    0.57
    UIControlState
    0.57
    Activations Density 1.260%

    No Known Activations