© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12415
    Prev
    Next
    INDEX
    Explanations

    expressions of mild emotion or acknowledgement, particularly "umm" and similar sounds, and also words implying difficulty or problems

    oai_token-act-pair · gemini-2.0-flash

    umm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     světě
    -0.45
     चीज़ों
    -0.45
    пенно
    -0.42
    
    -0.42
    ModelAdmin
    -0.42
     kör
    -0.40
    ContentAsync
    -0.40
    moveToNext
    -0.39
     internas
    -0.38
    Spread
    -0.37
    POSITIVE LOGITS
    Eloquent
    0.65
     MaterialApp
    0.60
     linkovi
    0.59
     Ribera
    0.59
    WireFormatLite
    0.59
    WebServlet
    0.58
    StackNavigator
    0.58
     smite
    0.58
     ویکی‌پدیای
    0.58
    ]--;
    0.57
    Activations Density 2.237%

    No Known Activations