© 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. 9502
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with discussion and expressing opinions

    oai_token-act-pair · gemini-2.0-flash

    comment

    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
     comment
    -2.25
     comments
    -2.11
    Comment
    -2.03
     Comment
    -2.00
     commenting
    -1.90
    comment
    -1.87
     Comments
    -1.78
    comments
    -1.75
     commented
    -1.73
    Comments
    -1.72
    POSITIVE LOGITS
     متعلقه
    0.96
    setVerticalGroup
    0.84
     Normdatei
    0.73
     IconData
    0.68
    醐
    0.67
     للاسماء
    0.66
    SharedDtor
    0.66
    UnsafeEnabled
    0.65
    InSection
    0.64
    MLLoader
    0.63
    Activations Density 6.395%

    No Known Activations