© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing negativity, failure, or wrongdoing on a large scale

    oai_token-act-pair · gemini-2.0-flash

    negativity

    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
     оригіналу
    -0.66
    تقاوى
    -0.65
     AssemblyCulture
    -0.64
     peor
    -0.58
     peores
    -0.57
     فريبيس
    -0.57
    oredCriteria
    -0.56
     mauvaise
    -0.56
    tagHelperRunner
    -0.54
    Worse
    -0.54
    POSITIVE LOGITS
     незавершена
    0.59
    Rè
    0.56
     autorytatywna
    0.56
    ratulations
    0.55
    HasAnnotation
    0.52
    getragen
    0.51
     actionMode
    0.50
    cheme
    0.49
    点了点头
    0.48
    ulage
    0.47
    Activations Density 4.029%

    No Known Activations