© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13050
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the possibility or ability to do something

    oai_token-act-pair · gemini-2.0-flash

    possibility and help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ↵↵
    -0.48
     link
    -0.40
     ready
    -0.38
     assured
    -0.38
    şı
    -0.38
    退
    -0.37
    زة
    -0.37
    setFirstName
    -0.37
     Hou
    -0.36
    queo
    -0.36
    POSITIVE LOGITS
    تقاوى
    0.94
     initComponents
    0.80
     Италијани
    0.78
     ویکی‌پدی
    0.78
    WithIOException
    0.77
     >=",
    0.76
    хьтан
    0.75
     transfieras
    0.73
    __(/*!
    0.72
     "..\..\
    0.71
    Activations Density 1.651%

    No Known Activations