© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13566
    Prev
    Next
    INDEX
    Explanations

    indented and numbered lists with lettered sub-items

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    +#+#
    -0.92
     ujednoznacz
    -0.89
     Paglinawan
    -0.87
    Personendaten
    -0.86
    MessageState
    -0.83
    GeneratedValue
    -0.83
    ReusableCell
    -0.81
    GEBURTS
    -0.79
    AddTagHelper
    -0.79
    findpost
    -0.79
    POSITIVE LOGITS
    .
    0.71
     high
    0.48
    ».
    0.47
    Пря
    0.46
    ).
    0.45
     tăng
    0.44
     vô
    0.44
    差
    0.43
     .
    0.43
    .”
    0.42
    Activations Density 1.408%

    No Known Activations