© 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. 3691
    Prev
    Next
    INDEX
    Explanations

    the characters "pa"

    oai_token-act-pair · gemini-2.0-flash

    pa

    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
     Waray
    -0.87
     <=",
    -0.78
     otomatig
    -0.75
     Италијани
    -0.75
     ddelweddau
    -0.68
     surla
    -0.67
     TextAlign
    -0.66
     Affiliations
    -0.66
     חיצוניים
    -0.65
    OrBuilder
    -0.65
    POSITIVE LOGITS
    ImageContext
    0.56
    pp
    0.51
    상
    0.46
    hal
    0.43
    hart
    0.42
     améliorer
    0.42
    ix
    0.42
    har
    0.42
    postcss
    0.41
    стями
    0.41
    Activations Density 0.470%

    No Known Activations