© 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. 15656
    Prev
    Next
    INDEX
    Explanations

    the first word of quoted statements or questions, and numbers.

    oai_token-act-pair · 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
     "..\..\
    -0.46
    RenderAtEndOf
    -0.45
    Jereo
    -0.39
    tainen
    -0.39
     model
    -0.39
    面上
    -0.39
     "..\..\..\
    -0.38
    DrawerToggle
    -0.38
    IMP
    -0.36
    MENAFN
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.79
    tagHelperRunner
    0.77
     onOptions
    0.73
    AsUp
    0.71
     oprot
    0.67
     noDo
    0.65
     Quis
    0.64
     WQS
    0.63
     SEDS
    0.63
    EnableWeb
    0.63
    Activations Density 2.757%

    No Known Activations