© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11495
    Prev
    Next
    INDEX
    Explanations

    code snippets including package imports and library calls

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
      
    -0.65
       
    -0.54
     
    -0.49
    ,
    -0.48
    ↵
    -0.48
    ?
    -0.47
     le
    -0.46
        
    -0.44
    ↵↵
    -0.44
     just
    -0.44
    POSITIVE LOGITS
    存于互联网档案馆
    1.02
     otomatig
    1.02
     myſelf
    1.02
     Efq
    1.02
    ^(@)
    0.96
    saraba
    0.96
     Houſe
    0.94
    CloseOperation
    0.94
     contextLoads
    0.93
    ՚
    0.92
    Activations Density 0.630%

    No Known Activations