© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12897
    Prev
    Next
    INDEX
    Explanations

    a mix of terms and symbols relating to math/code, medical issues, anatomy, and document formatting

    oai_token-act-pair · gemini-2.0-flash

    lib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    migrationBuilder
    -0.75
    ukone
    -0.68
     />);
    -0.56
    rceil
    -0.55
    อร
    -0.54
     NSCoder
    -0.53
    '].'
    -0.52
    enderror
    -0.52
    !*\
    -0.52
    ']):
    -0.51
    POSITIVE LOGITS
     doInBackground
    0.62
     tect
    0.56
     personnalité
    0.55
    JsonHelper
    0.53
    ParallelGroup
    0.53
    niosek
    0.52
    HttpPost
    0.50
    Portale
    0.50
     بيها
    0.49
    ToScroll
    0.48
    Activations Density 13.187%

    No Known Activations