© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated words and phrases in various contexts.

    oai_token-act-pair · gemini-2.0-flash

    Institutions and locations

    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
    íncia
    -0.69
    MemoryWarning
    -0.67
     protoimpl
    -0.64
    HasColumnType
    -0.62
    存于互联网档案馆
    -0.57
    awaiter
    -0.56
     CreateTagHelper
    -0.56
    SpringBootTest
    -0.56
    JspWriter
    -0.54
    ollectionView
    -0.54
    POSITIVE LOGITS
     purpoſe
    0.80
     myſelf
    0.75
     Efq
    0.75
     Jefus
    0.68
     Conſ
    0.68
     Majefty
    0.67
     pleaſure
    0.67
     himſelf
    0.66
     Reſ
    0.66
    ſelves
    0.65
    Activations Density 0.777%

    No Known Activations