© 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. 4418
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for mathematical and code block typesetting.

    oai_token-act-pair · gemini-2.0-flash

    computer 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
    Negative Logits
     '\\;'
    -0.66
    <bos>
    -0.58
    HasForeignKey
    -0.56
    Solve
    -0.51
     perfetto
    -0.50
     tohto
    -0.49
     devenus
    -0.47
     اعتماد
    -0.47
     qualifié
    -0.47
     againſt
    -0.47
    POSITIVE LOGITS
    hyrchwyd
    0.60
    IBOutlet
    0.57
    tangentMode
    0.56
    rrggbb
    0.56
    IBAction
    0.56
    Viitteet
    0.55
    timewa
    0.54
     iArr
    0.53
    addi
    0.53
    chromedriver
    0.52
    Activations Density 3.691%

    No Known Activations