© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    the word "ve" used as a contraction for "have" and words with positive sentiment, especially those used to describe objects

    oai_token-act-pair · gemini-2.0-flash

    ve

    np_max-act-logits · 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
     got
    -0.79
     disambiguazione
    -0.67
    Got
    -0.62
    got
    -0.60
    +:+
    -0.57
    (&:
    -0.56
    OrEqualTo
    -0.56
    ::<
    -0.55
    IUrlHelper
    -0.54
    Iné
    -0.54
    POSITIVE LOGITS
     obtain
    0.60
     obtained
    0.58
     vary
    0.56
    PYX
    0.54
     الرياضيه
    0.53
     AssemblyTitle
    0.52
     poveznice
    0.52
     observe
    0.49
    +#+#
    0.48
    Large
    0.47
    Activations Density 0.360%

    No Known Activations