© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6562
    Prev
    Next
    INDEX
    Explanations

    code snippets, potentially across multiple programming languages, with a strong focus on syntax and keywords.

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
     itſelf
    -0.82
     Efq
    -0.82
     myſelf
    -0.82
     themſelves
    -0.81
     Majefty
    -0.80
     Jefus
    -0.79
     Shakspeare
    -0.77
     photolibrary
    -0.77
     ویکی‌پدیای
    -0.76
     Houſe
    -0.76
    POSITIVE LOGITS
     searched
    0.39
     вы
    0.39
     pat
    0.39
     Optimize
    0.39
     pays
    0.39
    PLING
    0.39
    remove
    0.38
     passe
    0.38
     sc
    0.38
     Pay
    0.38
    Activations Density 5.608%

    No Known Activations