© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13128
    Prev
    Next
    INDEX
    Explanations

    words and phrases synonymous with "improving."

    oai_token-act-pair · gemini-2.0-flash

    improvements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     improvement
    -2.64
     Improvement
    -2.58
    Improvement
    -2.52
    improvement
    -2.50
    improve
    -2.48
     improved
    -2.47
     improvements
    -2.45
     improve
    -2.45
    improved
    -2.44
     Improvements
    -2.41
    POSITIVE LOGITS
     vast
    0.48
     isempty
    0.43
    vast
    0.43
    ras
    0.42
     dramatic
    0.41
    Vast
    0.41
    Swiper
    0.39
     fere
    0.38
    mado
    0.38
    atyana
    0.37
    Activations Density 2.161%

    No Known Activations