© 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. 318
    Prev
    Next
    INDEX
    Explanations

    a combination of miscellaneous code, court records, botanical information, expressions of emotion, and sports data.

    oai_token-act-pair · gemini-2.0-flash

    Miscellaneous text snippets

    np_max-act-logits · gemini-2.0-flash

    say "capitalized" Method used: 2 — all following tokens are capitalized; say "capitalized"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    -0.46
     Cæsar
    -0.42
     Pseud
    -0.37
     Ruf
    -0.36
     Aene
    -0.36
     Tamar
    -0.36
     Sopho
    -0.36
     Fiz
    -0.36
     Himself
    -0.36
     Puck
    -0.35
    POSITIVE LOGITS
    Surgery
    0.38
    Groundwater
    0.37
    Motorcycle
    0.37
    Expedition
    0.37
    Fitment
    0.37
    Diabetes
    0.36
    Dessert
    0.36
    Congratulations
    0.36
    Defendant
    0.36
    Planting
    0.36
    Activations Density 14.414%

    No Known Activations