© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9302
    Prev
    Next
    INDEX
    Explanations

    parts of code, or documentation

    oai_token-act-pair · gemini-2.0-flash

    code/formulas/database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sizeCache
    -0.95
    DockStyle
    -0.74
    detectChanges
    -0.70
     Shetterly
    -0.69
     Normdatei
    -0.69
    WaitGroup
    -0.69
    MessageOf
    -0.65
    GraphicsUnit
    -0.64
    LEncoder
    -0.63
     doInBackground
    -0.62
    POSITIVE LOGITS
    Демографія
    0.50
    tvguidetime
    0.46
    boten
    0.40
    msgTypes
    0.38
     Heinrich
    0.38
     meer
    0.37
    혁
    0.37
    DIALOG
    0.36
     righe
    0.36
     jButton
    0.36
    Activations Density 33.443%

    No Known Activations