© 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. 4762
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to Spanish food, science, and driving a car

    oai_token-act-pair · gemini-2.0-flash

    food or cars

    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
     autorytatywna
    -0.51
    tedì
    -0.50
    bedaan
    -0.47
    abestanden
    -0.47
    weist
    -0.47
     sat
    -0.46
     turn
    -0.46
    ījum
    -0.45
     tax
    -0.44
     worry
    -0.44
    POSITIVE LOGITS
    tableFuture
    0.72
     "..\..\
    0.69
    LEncoder
    0.64
    存于互联网档案馆
    0.64
    PerformLayout
    0.63
    脚注の使い方
    0.63
     الاطلاع
    0.62
    RunWith
    0.62
     AssemblyProduct
    0.60
    enumii
    0.59
    Activations Density 5.418%

    No Known Activations