© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5118
    Prev
    Next
    INDEX
    Explanations

    words that are ingredients or foods and words that describe cooking and food preparation.

    oai_token-act-pair · gemini-2.0-flash

    hot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     JADX
    -0.57
     كومونز
    -0.55
    giphy
    -0.52
    Rhestr
    -0.51
     AssemblyCompany
    -0.50
    cetamol
    -0.48
    casio
    -0.47
    httphttps
    -0.47
    ContentAsync
    -0.47
     balloon
    -0.46
    POSITIVE LOGITS
     hot
    1.68
    hot
    1.46
     Hot
    1.45
    Hot
    1.38
     HOT
    1.24
    HOT
    1.17
     hotter
    0.95
     hottest
    0.88
    ホット
    0.84
     nóng
    0.83
    Activations Density 2.812%

    No Known Activations