© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3859
    Prev
    Next
    INDEX
    Explanations

    terms related to a role-playing game, specifically character attributes and equipment

    oai_token-act-pair · gemini-2.0-flash

    Game skills

    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
    phosa
    -0.58
    مراجع
    -0.54
     PackageManager
    -0.53
    stdbool
    -0.52
     NUKAT
    -0.49
    Rhestr
    -0.48
     Lauder
    -0.47
    opheles
    -0.47
    elfde
    -0.47
     ویکی‌پدیای
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
     propOrder
    0.71
    KURZBESCHREIBUNG
    0.65
    AccessorTable
    0.64
    GOTREF
    0.58
     jScrollPane
    0.58
     كورة
    0.55
     <=",
    0.54
     وتسجيلات
    0.53
    انيف
    0.53
    Activations Density 12.222%

    No Known Activations