© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    words that mean "express".

    oai_token-act-pair · gemini-2.0-flash

    Words

    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
    RegressionTest
    -0.80
    
    -0.77
    mybatisplus
    -0.66
    DoubleQuotes
    -0.66
    IsContent
    -0.63
     surla
    -0.63
    UnitTesting
    -0.61
    IVEREF
    -0.60
     otomatig
    -0.60
     mergeFrom
    -0.59
    POSITIVE LOGITS
     words
    1.41
     Words
    1.17
     WORDS
    1.08
    words
    1.08
    Words
    1.02
     verbal
    1.00
     Worte
    0.94
     Verbal
    0.89
     word
    0.88
     language
    0.87
    Activations Density 1.366%

    No Known Activations