© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6554
    Prev
    Next
    INDEX
    Explanations

    the word "above", and other words and phrases that refer to a position or item previously mentioned

    oai_token-act-pair · gemini-2.0-flash

    above

    np_max-act · gemini-2.0-flash

    above

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     a
    -0.57
     No
    -0.56
     consist
    -0.51
    ↵↵
    -0.46
    No
    -0.44
     
    -0.44
     berupa
    -0.44
     sede
    -0.43
    a
    -0.43
     access
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.98
    ScopeManager
    0.98
     CURIAM
    0.97
    出版年
    0.92
     للمعارف
    0.90
    expandindo
    0.88
    TagMode
    0.87
    ureusement
    0.87
     NSCoder
    0.87
     ویکی‌پدیا
    0.84
    Activations Density 2.015%

    No Known Activations