© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    expensive jewelry and related phrases

    oai_token-act-pair · gemini-2.0-flash

    jewelry and gems

    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
     jewel
    -1.50
     Jewel
    -1.47
     diamond
    -1.46
     gem
    -1.44
     jewels
    -1.41
     Jewels
    -1.38
     DIAMOND
    -1.37
     Gems
    -1.36
     Diamond
    -1.35
     diamonds
    -1.34
    POSITIVE LOGITS
     string
    0.43
     surla
    0.40
    uter
    0.39
     Gretchen
    0.37
     ER
    0.36
    Lai
    0.36
    permitAll
    0.35
    toObject
    0.35
    elastic
    0.35
    onse
    0.35
    Activations Density 1.355%

    No Known Activations