© 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. 9208
    Prev
    Next
    INDEX
    Explanations

    code snippets and related programming or markup terminology

    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
    HasForeignKey
    -0.81
     &___
    -0.70
    /***/
    -0.63
    VersionUID
    -0.63
     consultato
    -0.62
     CreateTagHelper
    -0.58
     MainAxisSize
    -0.58
    Collegamenti
    -0.58
    JspWriter
    -0.58
    memoized
    -0.57
    POSITIVE LOGITS
     prisonniers
    0.52
     katkı
    0.50
     Aceite
    0.47
     håll
    0.47
     cương
    0.47
     bénévoles
    0.46
     esquerdo
    0.45
     médicas
    0.45
    gyű
    0.44
     coordon
    0.44
    Activations Density 17.982%

    No Known Activations