© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12621
    Prev
    Next
    INDEX
    Explanations

    words and phrases referring to language or speech patterns, and possibly nationality

    oai_token-act-pair · gemini-2.0-flash

    nationalities and accents

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

    languages/nationalities

    np_max-act-logits · gemini-2.0-flash

    accents

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Geraadpleegd
    -0.65
    tvguidetime
    -0.60
     propOrder
    -0.58
    EditorBrowsable
    -0.58
    Jîn
    -0.57
     Вікі
    -0.57
     PLWABN
    -0.57
     allAfrica
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    Liên
    -0.51
    POSITIVE LOGITS
     American
    1.00
     English
    0.83
     Irish
    0.80
    American
    0.79
     British
    0.79
     american
    0.77
     Australian
    0.74
     Italian
    0.73
     regional
    0.72
     southern
    0.68
    Activations Density 2.379%

    No Known Activations