© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10301
    Prev
    Next
    INDEX
    Explanations

    references to battles, wars, or political control of regions, particularly in historical contexts

    oai_token-act-pair · gemini-2.0-flash

    Holstein

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    AddHtmlAttribute
    -0.70
    __":
    -0.65
    __':
    -0.63
     <>",
    -0.61
    ană
    -0.60
    );?>
    -0.60
     مرئيه
    -0.60
     CreateTagHelper
    -0.57
     ReactDOM
    -0.57
    الإنجليزية
    -0.57
    POSITIVE LOGITS
    Czytaj
    0.46
     незавершена
    0.44
     elástica
    0.43
     propOrder
    0.40
    Сек
    0.40
    ginfo
    0.40
    ▼
    0.40
    afficheront
    0.40
     einzu
    0.40
    assis
    0.39
    Activations Density 2.238%

    No Known Activations