© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7141
    Prev
    Next
    INDEX
    Explanations

    words related to shoe product descriptions

    oai_token-act-pair · gemini-2.0-flash

    unique, patented

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WithIOException
    -0.60
    出版年
    -0.59
    RegressionTest
    -0.56
     NSCoder
    -0.56
    ]-->
    -0.56
    "?>
    -0.54
     références
    -0.54
    harusnya
    -0.53
    EditPart
    -0.53
    ViewInit
    -0.52
    POSITIVE LOGITS
     unique
    1.20
     patented
    1.13
     proprietary
    1.05
    Unique
    1.04
     patent
    1.03
    unique
    1.03
     Unique
    0.98
     exclusive
    0.94
     unieke
    0.91
    patent
    0.90
    Activations Density 1.632%

    No Known Activations