© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    general common words such as prepositions, conjunctions, pronouns, and other grammatical terms

    oai_token-act-pair · gemini-2.0-flash

    conjunction phrases

    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
     
    -0.55
    .
    -0.54
    !
    -0.49
     (
    -0.42
     .
    -0.42
     -
    -0.39
     for
    -0.37
     in
    -0.37
     or
    -0.36
    '
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    1.07
     myſelf
    1.04
    parsedMessage
    1.03
    NUMX
    1.02
     мәкал
    0.99
     ་་
    0.97
     архивлан
    0.96
    Vidite
    0.96
    ernalia
    0.96
    Personensuche
    0.95
    Activations Density 5.228%

    No Known Activations