© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4493
    Prev
    Next
    INDEX
    Explanations

    Spanish-language words and phrases related to programming and code logic

    oai_token-act-pair · gemini-2.0-flash

    que

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    databind
    -0.61
     which
    -0.60
     CreateTagHelper
    -0.56
    DataSetChanged
    -0.54
     contextLoads
    -0.52
    INCREF
    -0.52
    which
    -0.52
    asInstanceOf
    -0.49
     setw
    -0.49
     paisagem
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.81
    Хьажоргаш
    0.79
     незавершена
    0.66
    InitVars
    0.65
    脚注の使い方
    0.57
     appelez
    0.56
     ویکی‌پدی
    0.55
     оригіналу
    0.55
    kuuta
    0.55
     سكانية
    0.54
    Activations Density 0.799%

    No Known Activations