© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13441
    Prev
    Next
    INDEX
    Explanations

    text that describes the attributes and care of a plant

    oai_token-act-pair · gemini-2.0-flash

    terms related to classification or categorization

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     InputDecoration
    -0.82
     ModelExpression
    -0.70
    itemBuilder
    -0.67
     BoxDecoration
    -0.66
    addCriterion
    -0.66
    msgTypes
    -0.64
    脚注の使い方
    -0.63
    ollectionView
    -0.63
     Himo
    -0.62
    NewReader
    -0.62
    POSITIVE LOGITS
    ubehör
    0.53
     object
    0.50
     HERBERT
    0.50
     simb
    0.48
     rare
    0.48
     Kugel
    0.48
     Subjects
    0.48
    distributed
    0.48
    Distribución
    0.47
     subject
    0.47
    Activations Density 2.618%

    No Known Activations