© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8192
    Prev
    Next
    INDEX
    Explanations

    the word "drag", and secondarily numbers, especially in the context of mechanics or physics. John is also weakly triggered

    oai_token-act-pair · gemini-2.0-flash

    drag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.98
    ↵↵
    -0.97
     
    -0.93
    <eos>
    -0.81
      
    -0.77
     (
    -0.73
    -
    -0.70
    ,
    -0.70
    +
    -0.69
    2
    -0.68
    POSITIVE LOGITS
     Houſe
    1.59
     Theſe
    1.45
     ſeveral
    1.41
     itſelf
    1.38
     houſe
    1.34
     myſelf
    1.34
    ſelf
    1.34
     ―――――
    1.33
     Anſ
    1.33
     photolibrary
    1.32
    Activations Density 2.684%

    No Known Activations