© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and code symbols

    oai_token-act-pair · gemini-2.0-flash

    plus signs

    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
     autorytatywna
    -0.72
    fromnode
    -0.70
     ویکی‌پدی
    -0.65
    存于互联网档案馆
    -0.63
     NSCoder
    -0.62
    bonucleic
    -0.61
    complexContent
    -0.61
    kloped
    -0.61
    Jeografia
    -0.61
    PhysRev
    -0.60
    POSITIVE LOGITS
    <bos>
    1.45
     entgegen
    0.46
     muligt
    0.44
     let
    0.43
     eindeutig
    0.41
    følgelig
    0.41
     The
    0.40
     herum
    0.39
     wholeheartedly
    0.38
     blevet
    0.38
    Activations Density 3.606%

    No Known Activations