© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15867
    Prev
    Next
    INDEX
    Explanations

    words referring to tables and tasks in some structured dataset or code environment

    oai_token-act-pair · gemini-2.0-flash

    references to tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    the
    -0.94
    ting
    -0.86
    to
    -0.85
    tin
    -0.80
    table
    -0.79
    ten
    -0.77
    ters
    -0.74
    tes
    -0.73
    ter
    -0.71
    tra
    -0.71
    POSITIVE LOGITS
     T
    0.95
     TH
    0.95
     t
    0.93
     TI
    0.92
     Т
    0.90
     TA
    0.90
     TSM
    0.90
     TQ
    0.88
     TY
    0.88
     Tl
    0.88
    Activations Density 1.993%

    No Known Activations