© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13055
    Prev
    Next
    INDEX
    Explanations

    spatial adverbs and prepositions

    oai_token-act-pair · gemini-2.0-flash

    Location prepositions

    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
    帖最后由
    -0.80
    UnusedPrivate
    -0.77
    tagHelperRunner
    -0.71
    NameInMap
    -0.65
     Италијани
    -0.62
    Còn
    -0.60
     Мексичка
    -0.60
    kháu
    -0.59
     resté
    -0.58
    ніципа
    -0.57
    POSITIVE LOGITS
     in
    0.71
     away
    0.65
     inside
    0.64
     atop
    0.63
     up
    0.62
     around
    0.60
     within
    0.60
     down
    0.60
     beneath
    0.58
     above
    0.57
    Activations Density 0.770%

    No Known Activations