© 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. 8527
    Prev
    Next
    INDEX
    Explanations

    a mix of indentation, formatting characters, and uncommon punctuation specific to certain document styles.

    oai_token-act-pair · gemini-2.0-flash

    Mixed code and languages

    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
    rungsseite
    -0.92
    expandindo
    -0.78
    ंदीखरीदारी
    -0.68
    
    -0.64
     ویکی‌آمباردا
    -0.60
     bezeichneter
    -0.58
     '\\;'
    -0.58
    דש
    -0.56
    Демографія
    -0.55
     gynhyrchwyd
    -0.55
    POSITIVE LOGITS
    โครง
    0.61
    CompilerServices
    0.57
     defaultstate
    0.55
    ดอก
    0.54
    rawDesc
    0.54
    WriteTagHelper
    0.52
    จุด
    0.52
    TProtocol
    0.52
    แผ
    0.51
     onAnimation
    0.51
    Activations Density 1.363%

    No Known Activations