© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    words that appear in a description of food dishes at a restaurant

    oai_token-act-pair · gemini-2.0-flash

    Malaysian food and places

    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
    Rüyada
    -0.65
    новниш
    -0.59
    ContextHolder
    -0.56
    expandindo
    -0.55
    writeFieldEnd
    -0.52
    Referències
    -0.52
    ⓘ
    -0.51
    ьаж
    -0.50
     Walkover
    -0.50
    Попис
    -0.48
    POSITIVE LOGITS
     bawang
    0.66
     sayuran
    0.65
     kacang
    0.60
     kentang
    0.59
    cheiben
    0.59
     tepung
    0.57
    StoryboardSegue
    0.56
    cheibe
    0.55
    uarga
    0.54
     basah
    0.54
    Activations Density 0.228%

    No Known Activations