© 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. 4503
    Prev
    Next
    INDEX
    Explanations

    descriptions of dresses, especially those of high quality and style

    oai_token-act-pair · gemini-2.0-flash

    Clothes and fashion

    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
     Theodo
    -0.55
     Ezekiel
    -0.53
    Rüyada
    -0.53
    ніципалі
    -0.53
     Hades
    -0.52
     elim
    -0.52
    :✨
    -0.51
     Aphrodite
    -0.51
     Muss
    -0.51
     Madi
    -0.51
    POSITIVE LOGITS
     springfox
    0.56
    URLException
    0.56
    multirow
    0.55
    OGND
    0.50
    MigrationBuilder
    0.50
     remonter
    0.50
    WebVitals
    0.49
    Kjelder
    0.49
     finalement
    0.48
    WithMany
    0.48
    Activations Density 0.964%

    No Known Activations