© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2919
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly random words, some of which relate to dates, units of measure, or scientific terminology

    oai_token-act-pair · gemini-2.0-flash

    filler words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ordinaires
    -0.73
     définiti
    -0.72
     Monfieur
    -0.70
     médicale
    -0.69
     avoient
    -0.68
     ſtate
    -0.68
     rosse
    -0.67
     quæ
    -0.66
     purpoſe
    -0.65
     étrangère
    -0.65
    POSITIVE LOGITS
    1.13
    0.96
       
    0.95
      
    0.95
        
    0.93
     

    0.91
    Â
    0.88
    0.87
     ‌
    0.84
      
    0.83
    Activations Density 17.044%

    No Known Activations