© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11514
    Prev
    Next
    INDEX
    Explanations

    a variety of mathematical symbols within text, as well as some keywords like "level" and "stars".

    oai_token-act-pair · gemini-2.0-flash

    code/math expressions

    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
     purpoſe
    -0.79
     doubtnut
    -0.70
    ;">
    -0.70
     pleaſure
    -0.70
    €)
    -0.70
     plotly
    -0.69
     ]
    -0.69
    .")
    -0.68
     houſe
    -0.68
    !")
    -0.68
    POSITIVE LOGITS
    ंदीखरीदारी
    0.56
    
    0.55
    RegressionTest
    0.55
    ">//
    0.54
     crossorigin
    0.54
       
    0.52
    第
    0.50
        
    0.50
     kasarigan
    0.49
    '
    0.49
    Activations Density 3.437%

    No Known Activations