© 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. 13511
    Prev
    Next
    INDEX
    Explanations

    code blocks, comments, and related keywords in common programming languages

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    IntoConstraints
    -0.56
    ⓧ
    -0.52
    Parcelize
    -0.52
     EconPapers
    -0.48
    mybatisplus
    -0.45
    Eksteraj
    -0.44
     autorytatywna
    -0.44
     OFDb
    -0.44
     isSelected
    -0.43
     Consortium
    -0.41
    POSITIVE LOGITS
    <bos>
    1.17
    Хьажоргаш
    0.59
    RTLD
    0.56
    WriteBarrier
    0.56
    #+#
    0.55
    دانشنامهٔ
    0.54
     архивлан
    0.51
     consultato
    0.50
     uintptr
    0.50
    __((
    0.49
    Activations Density 2.320%

    No Known Activations