© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3648
    Prev
    Next
    INDEX
    Explanations

    code snippets, function definitions, and other programming language constructs.

    oai_token-act-pair · gemini-2.0-flash

    Code closing characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Dernière
    -0.50
     Réponses
    -0.43
    GEBURTSDATUM
    -0.43
     urbanization
    -0.41
     Chwiliwch
    -0.39
     interchangeably
    -0.38
     miniatur
    -0.38
    expandindo
    -0.37
     سكانية
    -0.37
     vigour
    -0.36
    POSITIVE LOGITS
    ↵
    0.81
    -\\
    0.65
    \}\\
    0.63
    .~(\
    0.62
     '/';
    0.62
    ,\\
    0.62
     émissions
    0.62
    rvore
    0.61
    =`
    0.61
     UIImageView
    0.60
    Activations Density 34.497%

    No Known Activations