© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4803
    Prev
    Next
    INDEX
    Explanations

    words relating to electronic systems or displays

    oai_token-act-pair · gemini-2.0-flash

    electronic systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AndEndTag
    -0.65
    ToScroll
    -0.57
    __(/*!
    -0.57
    keyframes
    -0.54
     Esq
    -0.54
    savefig
    -0.53
    __":
    -0.53
    astify
    -0.52
     DataTypes
    -0.52
    CreateMap
    -0.52
    POSITIVE LOGITS
    uncios
    0.53
    رشف
    0.50
    ècie
    0.47
     propOrder
    0.46
    masalah
    0.46
    irtschaft
    0.44
    ⓘ
    0.43
    essary
    0.41
     Navidad
    0.41
     zdjęć
    0.41
    Activations Density 30.134%

    No Known Activations