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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14880
    Prev
    Next
    INDEX
    Explanations

    the word "principles"

    oai_token-act-pair · gemini-2.0-flash

    principles

    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
    <bos>
    -2.00
     
    -0.97
    ↵↵
    -0.91
      
    -0.89
        
    -0.73
    <b>
    -0.73
    <strong>
    -0.71
     […]
    -0.68
       
    -0.67
    　
    -0.66
    POSITIVE LOGITS
     myſelf
    1.41
     pleaſure
    1.39
     purpoſe
    1.32
     houſe
    1.25
     Diſ
    1.20
     greateſt
    1.20
     himſelf
    1.18
     Monfieur
    1.17
     Majefty
    1.17
     RIPRODUZIONE
    1.16
    Activations Density 1.724%

    No Known Activations