© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15394
    Prev
    Next
    INDEX
    Explanations

    phrases like "bucket list" and HTML tags

    oai_token-act-pair · gemini-2.0-flash

    list

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rungsseite
    -0.71
     unknownFields
    -0.65
     مشين
    -0.61
    Vidite
    -0.59
    WindowEvent
    -0.58
    ngdoc
    -0.55
    fjspx
    -0.55
    Portale
    -0.54
    μερα
    -0.54
    ModelBuilder
    -0.54
    POSITIVE LOGITS
     list
    2.20
    list
    1.91
     lists
    1.84
     List
    1.70
     LIST
    1.68
    lists
    1.58
    LIST
    1.57
     lista
    1.55
     Lists
    1.52
    List
    1.52
    Activations Density 1.905%

    No Known Activations