© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15582
    Prev
    Next
    INDEX
    Explanations

    Japanese text and references to it

    oai_token-act-pair · gemini-2.0-flash

    Mixed English and Japanese text

    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
     Efq
    -1.02
    ſelf
    -0.98
     pleaſure
    -0.95
     purpoſe
    -0.93
     myſelf
    -0.93
     themſelves
    -0.92
     ſeveral
    -0.88
     raiſ
    -0.88
     ſtate
    -0.88
    neſs
    -0.87
    POSITIVE LOGITS
     Athenian
    0.21
    運
    0.21
    蓋
    0.21
    並
    0.21
    ↵↵
    0.20
    大陸
    0.20
     Odysseus
    0.20
    貢
    0.20
     Tiberius
    0.20
    問
    0.20
    Activations Density 3.482%

    No Known Activations