© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6281
    Prev
    Next
    INDEX
    Explanations

    reports of diseases and infections in specific geographic locations

    oai_token-act-pair · gemini-2.0-flash

    Medical testing/cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ]};
    -0.54
     BoxDecoration
    -0.51
     shadow
    -0.48
    ModelAndView
    -0.48
     }</
    -0.47
     ringer
    -0.47
     سكانية
    -0.47
     MenuView
    -0.47
    TY
    -0.45
    }}</
    -0.45
    POSITIVE LOGITS
    windowFixed
    0.58
     Мексичка
    0.58
    原始内容存档于
    0.56
    AllAfrica
    0.54
     Shakspeare
    0.54
    جوايز
    0.53
    Carriera
    0.53
    Дереккөздер
    0.52
     censiti
    0.51
     heapq
    0.50
    Activations Density 15.236%

    No Known Activations