© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    negations and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RegisterType
    -0.50
    (;;)
    -0.48
    #+#
    -0.47
     للاسماء
    -0.47
     way
    -0.47
    StructEnd
    -0.47
    NOSIS
    -0.46
    ousness
    -0.46
    WebElementEntity
    -0.45
    ToScroll
    -0.44
    POSITIVE LOGITS
    findpost
    0.65
    /**
    0.65
    iastical
    0.57
    principalColumn
    0.55
     ویکی‌آمباردا
    0.55
    возь
    0.54
    WithIOException
    0.54
     بيها
    0.54
    Források
    0.52
    iferous
    0.52
    Activations Density 3.509%

    No Known Activations