© 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. 13412
    Prev
    Next
    INDEX
    Explanations

    names of people along with some surrounding characters

    oai_token-act-pair · gemini-2.0-flash

    Short bios and articles

    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
    principalTable
    -0.79
    ьаж
    -0.73
    UserScript
    -0.72
    +#+#
    -0.66
    ']")
    -0.66
    </caption>
    -0.66
    CppMethod
    -0.65
    :✨
    -0.65
    ########.
    -0.64
     يتيمه
    -0.63
    POSITIVE LOGITS
     |
    0.62
     says
    0.56
     -
    0.52
    |
    0.51
     ·
    0.47
     mediates
    0.46
     artigian
    0.46
     –
    0.46
     describes
    0.45
    //
    0.45
    Activations Density 2.918%

    No Known Activations