© 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. 12350
    Prev
    Next
    INDEX
    Explanations

    bits of C++ code containing variable initializations and assignments, especially involving "m_" prefixes and timer-related names.

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    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
    punten
    -0.54
     للمعارف
    -0.51
     disambiguazione
    -0.49
    商品説明
    -0.47
    ıc
    -0.46
     समीक्षाओं
    -0.46
     propOrder
    -0.46
    пе
    -0.46
    adaptiveStyles
    -0.44
     iniz
    -0.44
    POSITIVE LOGITS
    MemoryWarning
    0.64
    GeneratedMessage
    0.64
    BagLayout
    0.59
    DebuggerNonUser
    0.58
     JSTOR
    0.57
    OrBuilder
    0.54
     stanovnika
    0.54
    setFlags
    0.54
    AlterField
    0.53
    5
    0.53
    Activations Density 11.967%

    No Known Activations