© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1820
    Prev
    Next
    INDEX
    Explanations

    java or javascript programming code

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     blessures
    -0.54
     scheda
    -0.51
     Server
    -0.50
    RectangleBorder
    -0.49
     [
    -0.49
     cerimonia
    -0.49
     recursos
    -0.48
     costos
    -0.48
     prisonniers
    -0.47
    luft
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.59
    횟
    0.59
    NewUrlParser
    0.57
    Collegamenti
    0.55
     tartalomajánló
    0.53
     مشين
    0.51
    LabelTagHelper
    0.51
     chloroform
    0.51
    ❋
    0.51
     nakalista
    0.50
    Activations Density 5.773%

    No Known Activations