© 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. 9616
    Prev
    Next
    INDEX
    Explanations

    words describing events either taking place or that have been completed

    oai_token-act-pair · gemini-2.0-flash

    events

    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
     led
    -1.27
     conducted
    -1.20
     presided
    -1.15
    conducted
    -1.13
     overseen
    -1.10
     chaired
    -1.09
    Led
    -1.09
     operated
    -1.07
     owned
    -1.05
     hosted
    -1.05
    POSITIVE LOGITS
    ecs
    0.48
     pó
    0.45
     toek
    0.43
    уда
    0.42
    のように
    0.40
     stik
    0.38
     Hes
    0.36
     gewicht
    0.36
    setLong
    0.36
    endront
    0.35
    Activations Density 15.418%

    No Known Activations