© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8106
    Prev
    Next
    INDEX
    Explanations

    descriptions of things moving through the air, or air quality.

    oai_token-act-pair · gemini-2.0-flash

    Air and air conditioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Air
    -2.44
     air
    -2.39
    Air
    -2.38
     AIR
    -2.20
    air
    -2.20
    AIR
    -2.09
     Airs
    -1.76
     Luft
    -1.65
     airs
    -1.64
     aire
    -1.59
    POSITIVE LOGITS
     concernés
    0.50
     africains
    0.49
     gela
    0.46
    azaki
    0.43
     identifiés
    0.42
     vendus
    0.42
     harganya
    0.40
     cruda
    0.39
     compone
    0.39
    stretchr
    0.39
    Activations Density 1.561%

    No Known Activations