© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13686
    Prev
    Next
    INDEX
    Explanations

    language surrounding environmental impact reduction especially regarding cars

    oai_token-act-pair · gemini-2.0-flash

    emissions/light/energy

    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
     emission
    -1.89
     emitting
    -1.75
     emit
    -1.75
     Emission
    -1.74
     emitted
    -1.73
     emissions
    -1.68
    Emission
    -1.65
     emits
    -1.65
     Emissions
    -1.64
    emission
    -1.57
    POSITIVE LOGITS
    الحياه
    0.50
     وتسجيلات
    0.46
    Batis
    0.44
    upol
    0.44
     stanovnika
    0.43
     FishBase
    0.43
     referenties
    0.43
    期刊论文
    0.43
    liers
    0.43
     المعرف
    0.42
    Activations Density 1.440%

    No Known Activations