© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    language expressing how items sold in the UK are poorly made and how cheaper items have changed society

    oai_token-act-pair · gemini-2.0-flash

    words related to cheap and Chinese goods

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

    Chinese cheap

    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
    dev
    -0.42
    lié
    -0.40
     PERT
    -0.39
    stad
    -0.38
    älte
    -0.36
     Nación
    -0.35
    目
    -0.34
    nungen
    -0.33
     empf
    -0.33
     Maude
    -0.33
    POSITIVE LOGITS
     Chinese
    1.21
     cheap
    1.18
     chinese
    1.15
     China
    1.12
     chines
    1.09
     CHINESE
    1.08
     china
    1.08
     cheaply
    1.07
     CHINA
    1.05
     cinese
    1.04
    Activations Density 1.425%

    No Known Activations