© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4321
    Prev
    Next
    INDEX
    Explanations

    programming code, especially in languages like C or Javascript, with some activation on Portuguese words, perhaps related to error messages or comments

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages

    np_max-act-logits · gemini-2.0-flash

    Portuguese

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    MemoryWarning
    -0.71
    хьтан
    -0.67
     red
    -0.64
    Jeografia
    -0.61
     Мексичка
    -0.59
     defaultstate
    -0.57
    المناصب
    -0.56
     Paglinawan
    -0.55
    Personensuche
    -0.55
    المشاركات
    -0.54
    POSITIVE LOGITS
     purpoſe
    0.59
     houſe
    0.55
    unehmen
    0.54
     թվական
    0.53
     uſe
    0.49
     noft
    0.47
     pleaſure
    0.46
     تانيه
    0.46
     ſche
    0.45
     occaf
    0.45
    Activations Density 1.360%

    No Known Activations