© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8499
    Prev
    Next
    INDEX
    Explanations

    the word "peace" and references to legal or governmental roles such as "justice".

    oai_token-act-pair · gemini-2.0-flash

    peace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     peace
    -3.13
     Peace
    -2.81
    Peace
    -2.78
    peace
    -2.77
     PEACE
    -2.55
    PEACE
    -2.33
     paix
    -1.85
     peaceful
    -1.67
    peaceful
    -1.51
     peacefully
    -1.48
    POSITIVE LOGITS
    XmlAccessorType
    0.79
     propOrder
    0.76
    دانشنامهٔ
    0.65
    HasForeignKey
    0.63
    Hochspringen
    0.62
    IUrlHelper
    0.62
     مرئيه
    0.59
    Хьажоргаш
    0.57
     kaynağından
    0.56
    <bos>
    0.55
    Activations Density 0.633%

    No Known Activations