© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13646
    Prev
    Next
    INDEX
    Explanations

    words related to software, planning, and data collection.

    oai_token-act-pair · gemini-2.0-flash

    Plus/Pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -1.23
    
    -1.23
     فريبيس
    -1.22
    脚注の使い方
    -1.21
     itſelf
    -1.19
     ویکی‌پدیا
    -1.16
    UnsafeEnabled
    -1.14
    ^(@)
    -1.13
    Personendaten
    -1.12
     Chwiliwch
    -1.11
    POSITIVE LOGITS
     Plus
    1.11
    Plus
    0.98
     II
    0.94
     pro
    0.94
     Pro
    0.91
    plus
    0.91
     plus
    0.90
    pro
    0.85
    Pro
    0.83
    +
    0.82
    Activations Density 1.642%

    No Known Activations