© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    celebrity gossip about wealthy people

    oai_token-act-pair · gemini-2.0-flash

    celebrity news

    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
    Negative Logits
     allmän
    -0.46
     to
    -0.46
     concetto
    -0.43
    ļi
    -0.42
     roupas
    -0.41
     cerámica
    -0.41
     consciência
    -0.41
    subsid
    -0.40
     for
    -0.40
     chapitre
    -0.39
    POSITIVE LOGITS
    PreferredItem
    1.00
    PerformLayout
    0.92
    ukone
    0.89
     nahilalakip
    0.88
    MLLoader
    0.86
     EconPapers
    0.85
     للاسماء
    0.82
    SourceChecksum
    0.82
     propOrder
    0.81
     poffible
    0.81
    Activations Density 0.475%

    No Known Activations