© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8032
    Prev
    Next
    INDEX
    Explanations

    words and phrases from legal or research documents that are technical in nature

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and formality

    np_max-act · gemini-2.0-flash
    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
     Mits
    -0.76
     Winaray
    -0.76
     Wigan
    -0.74
    Mits
    -0.73
     againſt
    -0.70
    |}{}
    -0.70
     leaſt
    -0.67
     ſeveral
    -0.65
     PRS
    -0.65
     finitely
    -0.64
    POSITIVE LOGITS
     препратки
    0.88
     Mara
    0.84
     snippetHide
    0.73
     SafeMath
    0.73
    FailureListener
    0.73
    querySelectorAll
    0.71
     calendriers
    0.71
     SEL
    0.71
    SEL
    0.69
     Carroll
    0.69
    Activations Density 8.324%

    No Known Activations