© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to climate science and atmospheric chemistry, especially those about ozone depletion

    oai_token-act-pair · gemini-2.0-flash

    ozone layer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     merece
    -0.57
    expandindo
    -0.57
    encodeWith
    -0.56
    IntoConstraints
    -0.54
    AndroidJUnit
    -0.51
    ngdoc
    -0.51
    AndEndTag
    -0.51
    principalTable
    -0.51
     onOptions
    -0.51
     resourceCulture
    -0.51
    POSITIVE LOGITS
    oa̍t
    0.76
     actionMode
    0.65
     odkazy
    0.63
    MENAFN
    0.56
     تانيه
    0.55
    ArrowToggle
    0.54
     upper
    0.54
     lower
    0.54
    Lower
    0.53
    protoimpl
    0.51
    Activations Density 1.112%

    No Known Activations