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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12333
    Prev
    Next
    INDEX
    Explanations

    references to artwork and creation, especially regarding textiles, while also activating on somewhat random nouns and adjectives

    oai_token-act-pair · gemini-2.0-flash

    art

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    PANY
    -0.57
    SearchTree
    -0.55
    Jeografia
    -0.53
     Curie
    -0.53
     GG
    -0.52
    Geograf
    -0.50
    
    -0.50
    Seller
    -0.49
    Bloc
    -0.48
     IconData
    -0.48
    POSITIVE LOGITS
     art
    1.94
     Art
    1.59
    art
    1.56
    Art
    1.49
     ART
    1.20
    ART
    1.09
    アート
    0.98
     искусство
    0.93
    艺术
    0.84
     arts
    0.83
    Activations Density 3.999%

    No Known Activations