© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10584
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code Snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NOPQRST
    -0.56
     EdgeInsets
    -0.54
    rådet
    -0.52
     coeur
    -0.50
     ujednoznacz
    -0.50
     noDo
    -0.50
    ANIUM
    -0.50
     verso
    -0.49
    — 
    -0.49
     acu
    -0.48
    POSITIVE LOGITS
     Савезне
    0.67
     HasFactory
    0.63
    ніципа
    0.59
     JTable
    0.57
     سكانية
    0.55
     Bourgoin
    0.52
     kasarigan
    0.51
     Paglinawan
    0.50
    angor
    0.50
     useAuth
    0.49
    Activations Density 4.605%

    No Known Activations