© 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. 4288
    Prev
    Next
    INDEX
    Explanations

    code snippets including hex color values and region/code pairs

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ريكية
    -0.46
    ycznie
    -0.46
    us
    -0.45
    (
    -0.44
     
    -0.44
    -
    -0.43
     encantan
    -0.41
    usza
    -0.41
    [
    -0.41
    <i>
    -0.40
    POSITIVE LOGITS
     myſelf
    0.77
     Monfieur
    0.75
     विश्वसनीयता
    0.72
    ंदीखरीदारी
    0.69
    WithIOException
    0.67
     fubject
    0.67
     Biôgrafia
    0.66
    ourite
    0.66
     виправивши
    0.65
     Sénat
    0.65
    Activations Density 7.039%

    No Known Activations