© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 698
    Prev
    Next
    INDEX
    Explanations

    code snippets or data structures, specifically those related to statuses and states, and possibly configuration or database related items

    oai_token-act-pair · gemini-2.0-flash

    Code and statuses

    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
    PreferredItem
    -0.72
     createSprite
    -0.70
     ویکی‌آمباردا
    -0.69
     bezeichneter
    -0.69
     Мексичка
    -0.68
     Chwiliwch
    -0.67
     للمعارف
    -0.67
     мәкал
    -0.65
    JTable
    -0.63
     BoxFit
    -0.63
    POSITIVE LOGITS
    wrote
    0.53
    couldn
    0.53
    managing
    0.49
    suspended
    0.48
    funded
    0.48
    Replacing
    0.47
    billed
    0.47
    fetched
    0.47
    closing
    0.46
    leaved
    0.46
    Activations Density 10.290%

    No Known Activations