© 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. 9008
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of contexts including code, numbers, and technical descriptions, and may be activating on indentation or spacing

    oai_token-act-pair · gemini-2.0-flash

    Code and technical snippets

    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
     three
    -0.65
    three
    -0.58
     five
    -0.58
    3
    -0.55
     Three
    -0.55
     createState
    -0.53
    1
    -0.52
    5
    -0.52
    THREE
    -0.52
     Five
    -0.51
    POSITIVE LOGITS
    SharedCtor
    0.61
     ویکی‌پدیا
    0.58
    InjectAttribute
    0.57
     الحره
    0.56
     يتيمه
    0.53
    2
    0.52
    coroutines
    0.52
     २०
    0.51
    Geplaatst
    0.50
    Fourth
    0.50
    Activations Density 4.141%

    No Known Activations