© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3570
    Prev
    Next
    INDEX
    Explanations

    the term "machine learning"

    oai_token-act-pair · gemini-2.0-flash

    learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     مشين
    -1.02
    ंदीखरीदारी
    -0.94
    Rüyada
    -0.86
    +:+
    -0.82
    StructEnd
    -0.78
     оригіналу
    -0.78
     jScrollPane
    -0.77
    expandindo
    -0.73
     Мексичка
    -0.69
    verwijspagina
    -0.68
    POSITIVE LOGITS
     propOrder
    0.59
     AI
    0.58
    ArgsConstructor
    0.52
     poros
    0.48
    cipy
    0.46
    y
    0.45
    Most
    0.44
     modeling
    0.43
     Most
    0.43
    AI
    0.43
    Activations Density 0.253%

    No Known Activations