© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8305
    Prev
    Next
    INDEX
    Explanations

    the word "coefficient," sometimes in proximity to the word "exception" or "versa"

    oai_token-act-pair · gemini-2.0-flash

    coefficient

    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
     ‘
    -0.86
     name
    -0.84
     “
    -0.81
     
    -0.79
     the
    -0.77
     life
    -0.75
     status
    -0.73
     people
    -0.73
     national
    -0.72
     under
    -0.71
    POSITIVE LOGITS
     fumée
    0.94
    Xna
    0.94
     vectorielles
    0.93
     termica
    0.93
     caribou
    0.91
     employes
    0.91
     Athenians
    0.90
     republics
    0.89
     Assyrian
    0.89
     parishes
    0.88
    Activations Density 2.027%

    No Known Activations