© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6369
    Prev
    Next
    INDEX
    Explanations

    research publications that use or discuss big datasets and feature selection algorithms

    oai_token-act-pair · gemini-2.0-flash

    data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Wiktionnaire
    -0.63
     كومونز
    -0.62
    ModelBuilder
    -0.61
    ifrance
    -0.61
     transfieras
    -0.61
    PerformLayout
    -0.58
    ########.
    -0.56
    XmlType
    -0.56
     hạng
    -0.54
    #+#
    -0.54
    POSITIVE LOGITS
     data
    1.80
    data
    1.41
     Data
    1.33
    データ
    1.28
     DATA
    1.26
    Data
    1.24
    数据
    1.22
     Daten
    1.22
     dataset
    1.20
     données
    1.19
    Activations Density 2.861%

    No Known Activations