© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13547
    Prev
    Next
    INDEX
    Explanations

    words indicating comparison

    oai_token-act-pair · gemini-2.0-flash

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Madura
    -0.66
     myſelf
    -0.59
     Theſe
    -0.57
     varandra
    -0.56
    DialogContent
    -0.56
     communs
    -0.56
    prnewswire
    -0.55
     Monfieur
    -0.55
     Thebes
    -0.55
     båda
    -0.54
    POSITIVE LOGITS
    GraphicsUnit
    0.63
    PerformLayout
    0.61
    AddHtmlAttribute
    0.60
    
    0.59
    WithMany
    0.58
    Tikang
    0.55
     surla
    0.54
    WaitGroup
    0.52
    IBOutlet
    0.52
    Externé
    0.50
    Activations Density 2.945%

    No Known Activations