© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9908
    Prev
    Next
    INDEX
    Explanations

    a mix of chinese-related locations, food and names.

    oai_token-act-pair · gemini-2.0-flash

    Li

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Li
    -2.03
    Li
    -1.88
     li
    -1.87
    li
    -1.37
     LI
    -1.36
    LI
    -1.17
     Lipp
    -1.02
     Ли
    -1.01
     Lib
    -0.98
     LIP
    -0.94
    POSITIVE LOGITS
    MigrationBuilder
    0.67
    Népesség
    0.52
     ICS
    0.52
     الحره
    0.51
     riuscito
    0.50
     Eup
    0.49
     smě
    0.49
     TDI
    0.49
     žiad
    0.48
    modity
    0.48
    Activations Density 10.165%

    No Known Activations