© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    mentions of anniversaries or birthdays

    oai_token-act-pair · gemini-2.0-flash

    anniversary

    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
    Negative Logits
     myſelf
    -1.99
     Efq
    -1.90
     Majefty
    -1.84
     itſelf
    -1.82
     purpoſe
    -1.82
     Jefus
    -1.78
     himſelf
    -1.74
    ſelf
    -1.74
     Monfieur
    -1.70
     pleaſure
    -1.64
    POSITIVE LOGITS
      
    0.92
     
    0.84
     M
    0.82
     B
    0.77
     a
    0.76
     l
    0.74
     E
    0.73
     con
    0.71
    ,
    0.70
     an
    0.69
    Activations Density 0.773%

    No Known Activations