© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5006
    Prev
    Next
    INDEX
    Explanations

    code with heavy templating and/or comments in it

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    脚注の使い方
    -0.76
    ArrowToggle
    -0.66
    PositiveButton
    -0.60
    mybatisplus
    -0.58
    LabelTagHelper
    -0.54
     onPostExecute
    -0.53
    DialogContent
    -0.51
     ITIS
    -0.51
     EClass
    -0.50
     insuffisamment
    -0.49
    POSITIVE LOGITS
    dotte
    0.61
     noires
    0.53
     prácti
    0.52
     dott
    0.52
    よかった
    0.52
    CopyWith
    0.51
     rendus
    0.50
     Walkover
    0.50
    elance
    0.49
     مراق
    0.49
    Activations Density 1.022%

    No Known Activations