© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    environmental topics, especially climate change and related issues like ozone depletion, greenhouse gases, and air pollution

    oai_token-act-pair · gemini-2.0-flash

    climate

    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
     vectorielle
    -0.66
     mergeFrom
    -0.65
    Portale
    -0.65
    WriteLiteral
    -0.58
    الحياه
    -0.52
     getItemCount
    -0.52
    واع
    -0.52
     đó
    -0.52
    Portail
    -0.51
     Skies
    -0.51
    POSITIVE LOGITS
    StoryboardSegue
    0.56
     مشين
    0.55
    ValueStyle
    0.54
    parsedMessage
    0.54
     chi̍t
    0.53
     FetchType
    0.52
     change
    0.52
    ัจ
    0.51
     MainAxisSize
    0.49
    Personensuche
    0.49
    Activations Density 0.817%

    No Known Activations