© 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. 5511
    Prev
    Next
    INDEX
    Explanations

    the word "master" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    master

    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
     …
    -0.76
    3
    -0.72
    5
    -0.68
    0
    -0.66
    1
    -0.63
    van
    -0.63
    2
    -0.61
    梁
    -0.61
    4
    -0.60
    ———
    -0.59
    POSITIVE LOGITS
     propOrder
    0.98
     houſe
    0.97
    DockStyle
    0.96
     Италијани
    0.95
     raiſ
    0.93
     pleaſure
    0.92
     Roskov
    0.91
     deſt
    0.90
     purpoſe
    0.87
     pleaf
    0.86
    Activations Density 1.237%

    No Known Activations