© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    general conversational filler and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    online discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    الإنجليزية
    -0.58
    SuccessListener
    -0.55
    mtrl
    -0.54
    sizeCache
    -0.54
    NameInMap
    -0.52
    arım
    -0.51
    gebra
    -0.48
     ujednoznacz
    -0.47
    StructEnd
    -0.47
    onAttach
    -0.47
    POSITIVE LOGITS
     mergeFrom
    0.72
     Paglinawan
    0.71
    archiviato
    0.62
     intptr
    0.54
    Personendaten
    0.53
     declarar
    0.48
    gway
    0.48
    Throwaway
    0.47
     BoxFit
    0.46
     EClass
    0.46
    Activations Density 1.974%

    No Known Activations