© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9893
    Prev
    Next
    INDEX
    Explanations

    percent encoded URLs

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ↵
    -0.53
    5
    -0.48
      
    -0.48
     [
    -0.48
    4
    -0.47
    ↵↵
    -0.47
     
    -0.47
     n
    -0.46
     $
    -0.46
     I
    -0.44
    POSITIVE LOGITS
     Efq
    0.86
    SequentialGroup
    0.82
     MotionEvent
    0.81
    
    0.80
     /\.(
    0.80
    PreAuthorize
    0.78
    BeginContext
    0.78
     /\.
    0.77
     كومونز
    0.77
     يتيمه
    0.75
    Activations Density 1.025%

    No Known Activations