© 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. 8193
    Prev
    Next
    INDEX
    Explanations

    words used in formal documents, reports, and computer code licenses

    oai_token-act-pair · gemini-2.0-flash

    technical papers

    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
     Of
    -2.13
    Of
    -2.13
     OF
    -2.09
    OF
    -1.99
    of
    -1.55
    OfThe
    -1.27
     de
    -1.13
    OfWork
    -1.09
    ofthe
    -1.00
    ofs
    -0.98
    POSITIVE LOGITS
    ItemStack
    0.53
    icolon
    0.46
    جغرافيا
    0.45
    Geplaatst
    0.45
    TagMode
    0.44
    hazi
    0.44
    iertas
    0.43
    TimeUnit
    0.42
    JNIEnv
    0.42
    /**
    
    0.42
    Activations Density 1.919%

    No Known Activations