© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15791
    Prev
    Next
    INDEX
    Explanations

    words related to research, medical studies, and statistical reporting of numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     autorytatywna
    -0.77
     '\\;'
    -0.75
    principalColumn
    -0.75
    PropertyChanging
    -0.65
     EconPapers
    -0.64
    +#+#
    -0.64
    Билгалдахарш
    -0.64
    NameInMap
    -0.64
    LEGGI
    -0.63
    RegressionTest
    -0.63
    POSITIVE LOGITS
    MemoryWarning
    0.54
    })`
    0.48
     fous
    0.47
    ահ
    0.45
    slidesToShow
    0.44
    classnames
    0.42
     Dilution
    0.42
    bitField
    0.41
     sinu
    0.40
    tilde
    0.40
    Activations Density 51.016%

    No Known Activations