© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4052
    Prev
    Next
    INDEX
    Explanations

    the names of Japanese people and elements of Java code

    oai_token-act-pair · gemini-2.0-flash

    Japanese 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    protoimpl
    -0.57
    matum
    -0.55
    ніципалі
    -0.54
    ญี่ปุ่น
    -0.53
     насељу
    -0.52
     Și
    -0.52
    SharedDtor
    -0.51
     nomi
    -0.50
    umi
    -0.50
    basicConfig
    -0.49
    POSITIVE LOGITS
    berday
    0.58
     poussière
    0.54
     typelib
    0.53
    \|^{
    0.51
    gång
    0.51
     extérieure
    0.50
     comunión
    0.49
     réduite
    0.49
     mobilité
    0.49
     prá
    0.48
    Activations Density 0.147%

    No Known Activations