© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8210
    Prev
    Next
    INDEX
    Explanations

    the word "animal," and the word "together."

    oai_token-act-pair · gemini-2.0-flash

    animal

    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
     
    -0.98
     sub
    -0.82
     Sub
    -0.82
    /
    -0.80
      
    -0.79
     R
    -0.79
     S
    -0.78
     D
    -0.77
     “
    -0.76
     Black
    -0.76
    POSITIVE LOGITS
     photolibrary
    1.12
     Efq
    1.06
     Huguen
    1.05
     doubtnut
    0.99
     synag
    0.98
     Muses
    0.97
    windowFixed
    0.96
     auffi
    0.95
     Pyrene
    0.93
     ་་
    0.93
    Activations Density 0.673%

    No Known Activations