© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11387
    Prev
    Next
    INDEX
    Explanations

    HTML code for links and ampersands

    oai_token-act-pair · gemini-2.0-flash

    amp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     للمعارف
    -0.96
    ########.
    -0.94
    انيف
    -0.89
    <bos>
    -0.87
    InstrumentedTest
    -0.82
    IContainer
    -0.81
     تضيفلها
    -0.77
    SourceChecksum
    -0.74
     Мексичка
    -0.73
    ագրություններ
    -0.72
    POSITIVE LOGITS
    seamnă
    0.55
    といけない
    0.51
     self
    0.50
     top
    0.48
    chong
    0.46
     gekomen
    0.45
    uudet
    0.44
     Ara
    0.42
     ساتھ
    0.42
     rest
    0.41
    Activations Density 0.755%

    No Known Activations