© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13582
    Prev
    Next
    INDEX
    Explanations

    HTML table structures with radio button inputs

    oai_token-act-pair · gemini-2.0-flash

    HTML table tags

    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
    hang
    -0.47
    hung
    -0.46
     бы
    -0.46
     cardinal
    -0.46
     Would
    -0.46
     HANG
    -0.44
    would
    -0.44
    USET
    -0.44
     lccn
    -0.44
    oneg
    -0.44
    POSITIVE LOGITS
    IsContent
    0.91
    WebVitals
    0.71
    matchCondition
    0.71
    NameInMap
    0.68
    styleType
    0.68
    Personensuche
    0.66
     defaultstate
    0.65
    InSection
    0.65
     ويكيپيديا
    0.64
    Personendaten
    0.62
    Activations Density 0.805%

    No Known Activations