© 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. 9552
    Prev
    Next
    INDEX
    Explanations

    text that looks like HTML or XML tags

    oai_token-act-pair · gemini-2.0-flash

    <

    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
    <
    -0.93
    <bos>
    -0.84
    /*
    -0.55
    mybatisplus
    -0.53
    BeginContext
    -0.52
     layui
    -0.48
    ierende
    -0.47
    日閲覧
    -0.47
    aisons
    -0.47
    RSpec
    -0.46
    POSITIVE LOGITS
     ddelweddau
    0.57
    ochem
    0.56
    ApplicationTests
    0.56
    Obrázky
    0.54
    pinephrine
    0.54
     Вікі
    0.52
    انيف
    0.52
     uintptr
    0.52
    GOTREF
    0.52
    AlterField
    0.51
    Activations Density 0.543%

    No Known Activations