© 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. 13216
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Javascript and CSS

    oai_token-act-pair · gemini-2.0-flash

    blur focus

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.85
     CreateTagHelper
    -0.78
    +#+#
    -0.73
     дописавши
    -0.71
    :✨
    -0.70
    reactstrap
    -0.69
    ViewImports
    -0.68
    SerializedName
    -0.67
     autorytatywna
    -0.66
    '])){
    -0.65
    POSITIVE LOGITS
     TextEditing
    0.50
     resourceCulture
    0.44
     قلم
    0.43
    ποίη
    0.43
     momento
    0.43
    تمام
    0.42
    fieldLabel
    0.40
    ViewStyle
    0.40
    MethodManager
    0.40
    ilaian
    0.39
    Activations Density 0.890%

    No Known Activations