© 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. 4359
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate something is being improved or better understood

    oai_token-act-pair · gemini-2.0-flash

    improvement

    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
    <bos>
    -0.79
     tartalomajánló
    -0.70
    GEBURTSDATUM
    -0.68
    Tikang
    -0.65
     purpoſe
    -0.63
     Hift
    -0.60
     ſeveral
    -0.59
     rechange
    -0.58
    matchCondition
    -0.58
     Shakspeare
    -0.57
    POSITIVE LOGITS
     insuffisamment
    0.59
    AccessorTable
    0.54
    果た
    0.50
    ndice
    0.49
    はじめに
    0.49
     dich
    0.47
    plik
    0.47
     Ham
    0.47
     assolu
    0.46
    wner
    0.46
    Activations Density 1.378%

    No Known Activations