© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 7986
    Prev
    Next
    INDEX
    Explanations

    code comments describing allocation, addition, and termination of objects

    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_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Waray
    -0.51
    onomía
    -0.49
     oprot
    -0.48
    HtmlAttribute
    -0.48
    SequentialGroup
    -0.47
     rind
    -0.47
    GraphicsUnit
    -0.45
     silang
    -0.44
    cinogen
    -0.44
     Corintios
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.70
    IntoConstraints
    0.65
     initComponents
    0.61
     BrowserModule
    0.59
    AndEndTag
    0.56
    MLLoader
    0.56
    ագրություններ
    0.55
    providedIn
    0.54
     ujednoznacz
    0.53
     ddelweddau
    0.53
    Activations Density 0.647%

    No Known Activations