Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12168
    Prev
    Next
    INDEX
    Explanations

    programming code, especially related to string manipulation, data structures, and file formats or markup.

    oai_token-act-pair · gemini-2.0-flash

    Programming and international text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IFORNIA
    -0.61
    học
    -0.58
    ilingual
    -0.52
    OOTDTY
    -0.52
    Và
    -0.52
    Màu
    -0.52
    TINGS
    -0.51
    imothy
    -0.51
    tôi
    -0.51
    Fazit
    -0.50
    POSITIVE LOGITS
     Dumnezeu
    0.63
     Ptolemy
    0.60
     prieten
    0.56
     barbati
    0.56
     îna
    0.56
     Vedi
    0.56
     quæ
    0.55
     Să
    0.54
     copii
    0.54
     pleaſure
    0.54
    Activations Density 12.251%

    No Known Activations