© 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. 5191
    Prev
    Next
    INDEX
    Explanations

    the word "dedicated", and sometimes words relating to cemeteries

    oai_token-act-pair · gemini-2.0-flash

    dedicated

    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
    
    -1.09
    ](#
    -1.05
    .")
    -1.02
    )");
    -1.00
    ")));
    -1.00
    ureusement
    -0.97
    SBATCH
    -0.95
     سكانية
    -0.95
    ỡng
    -0.94
    UnusedPrivate
    -0.94
    POSITIVE LOGITS
    asa
    0.61
     eg
    0.59
    可
    0.58
                  
    0.56
            
    0.56
               
    0.56
    もの
    0.55
    （
    0.54
       
    0.54
    !=
    0.54
    Activations Density 2.157%

    No Known Activations