© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4348
    Prev
    Next
    INDEX
    Explanations

    words with a positive connotation related to progress.

    oai_token-act-pair · gemini-2.0-flash

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     improve
    -2.09
     improvement
    -2.05
     improved
    -1.96
     improving
    -1.92
     improvements
    -1.91
    improve
    -1.90
     improves
    -1.89
     Improvement
    -1.88
     Improve
    -1.84
    improved
    -1.82
    POSITIVE LOGITS
     jScrollPane
    0.71
     nakalista
    0.63
    DialogContent
    0.63
     onCancelled
    0.55
    "?>
    0.54
    MLLoader
    0.50
     trữ
    0.49
     Suff
    0.48
    TAINS
    0.48
    ثم
    0.48
    Activations Density 3.386%

    No Known Activations