© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to file paths, binding and dependencies

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    ®
    -0.62
     Tuttle
    -0.59
     Chapman
    -0.58
     Ricardo
    -0.58
    ％
    -0.56
     kertas
    -0.56
    XmlAccessorType
    -0.55
    Ricardo
    -0.55
    (\
    -0.55
    iser
    -0.53
    POSITIVE LOGITS
     McNally
    0.66
     Barton
    0.63
     Teb
    0.60
     Scooby
    0.58
    Rüyada
    0.57
     Normdatei
    0.57
     Mee
    0.57
     Cang
    0.56
     Speedway
    0.56
     Titus
    0.56
    Activations Density 9.186%

    No Known Activations