© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12314
    Prev
    Next
    INDEX
    Explanations

    a variety of formatting and structural elements, including mathematical notation, html tags, list items, labels, and common phrases

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MaterialApp
    -0.76
    Obrázky
    -0.75
     ddelweddau
    -0.75
     ―――――
    -0.72
    ISupport
    -0.69
    didSet
    -0.68
     TextInputType
    -0.67
    دانشنامهٔ
    -0.66
     CommandType
    -0.65
     Efq
    -0.65
    POSITIVE LOGITS
     yourself
    0.66
     your
    0.61
    yourself
    0.60
     Yourself
    0.59
    your
    0.51
     yourselves
    0.49
     YOURSELF
    0.47
     Your
    0.46
     publiques
    0.46
     soyez
    0.46
    Activations Density 3.075%

    No Known Activations