© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    code-related tokens that aren't words, especially indentation and formatting

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    dge
    -0.52
    /**
    -0.51
    ramid
    -0.50
     firebaseConfig
    -0.50
     Гото
    -0.50
     @"/
    -0.50
    LLocation
    -0.50
     تكبرها
    -0.50
    Archite
    -0.49
    DIPSETTING
    -0.49
    POSITIVE LOGITS
     ProtoMessage
    0.74
               
    0.58
    ाहरण
    0.56
                
    0.54
                  
    0.54
                 
    0.52
              
    0.52
                    
    0.51
                     
    0.49
                          
    0.49
    Activations Density 0.370%

    No Known Activations