© 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. 6252
    Prev
    Next
    INDEX
    Explanations

    terms and names related to law, locations, sports and organizations

    oai_token-act-pair · gemini-2.0-flash

    place names

    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
     myſelf
    -2.16
     Efq
    -2.09
     Monfieur
    -2.03
     Jefus
    -2.02
     itſelf
    -1.96
     Majefty
    -1.96
     purpoſe
    -1.95
     Anſ
    -1.94
     auffi
    -1.90
     Diſ
    -1.86
    POSITIVE LOGITS
     
    1.10
      
    0.95
     (
    0.90
     A
    0.88
     I
    0.88
    ↵
    0.86
     The
    0.85
       
    0.84
     T
    0.83
     P
    0.83
    Activations Density 4.441%

    No Known Activations