© 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. 11565
    Prev
    Next
    INDEX
    Explanations

    words related to mathematics, formal language, and the law

    oai_token-act-pair · gemini-2.0-flash

    attributes of properties or qualities

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

    words ending in -ity/-ness

    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
     malheure
    -0.59
     bezpiecz
    -0.56
     naturligt
    -0.52
     ſtand
    -0.50
     aéreas
    -0.50
     cauſe
    -0.49
     infeliz
    -0.49
     jambe
    -0.49
    合理的
    -0.48
     dobre
    -0.47
    POSITIVE LOGITS
     solidity
    0.84
     simplicity
    0.80
    queness
    0.78
     freshness
    0.77
    WebServlet
    0.76
    eness
    0.75
     purity
    0.74
    uteness
    0.73
    ishness
    0.73
     elegance
    0.73
    Activations Density 3.410%

    No Known Activations