© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12764
    Prev
    Next
    INDEX
    Explanations

    legal, political, or business conflicts and the language associated with how they are dealt with

    oai_token-act-pair · gemini-2.0-flash

    legal/diplomatic disputes

    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
     nahilalakip
    -0.61
    makeConstraints
    -0.60
    SharedCtor
    -0.58
    ]][
    -0.57
     مشين
    -0.56
     Voice
    -0.55
    RegressionTest
    -0.55
    
    -0.54
    
    -0.52
     sopra
    -0.51
    POSITIVE LOGITS
     pleaſure
    0.58
     الرياضيه
    0.56
    Réalisation
    0.55
     Shakspeare
    0.55
    centralwidget
    0.54
     vPvB
    0.52
    ContentAsync
    0.52
    brough
    0.51
    ulsory
    0.50
    nown
    0.49
    Activations Density 0.489%

    No Known Activations