© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3727
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to system load and distribution

    oai_token-act-pair · gemini-2.0-flash

    capacity and demand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Източници
    -0.72
     ModelExpression
    -0.67
    __*/
    -0.53
    kháu
    -0.52
    kuuta
    -0.52
     initComponents
    -0.52
     Overflow
    -0.51
    ViewFeatures
    -0.50
    tanleria
    -0.50
    __':
    -0.49
    POSITIVE LOGITS
     télévisée
    0.56
     deafness
    0.55
    ffindor
    0.51
     وتسجيلات
    0.51
    kusen
    0.50
     negru
    0.49
     Ordovician
    0.49
     morire
    0.49
     larmes
    0.49
     civiles
    0.48
    Activations Density 40.036%

    No Known Activations