© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13509
    Prev
    Next
    INDEX
    Explanations

    symbols, code snippets, and related terms.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     instead
    -0.86
    instead
    -0.81
     Instead
    -0.81
    Instead
    -0.79
     invece
    -0.69
    webElementXpaths
    -0.63
     rather
    -0.61
    __(/*!
    -0.60
     yerine
    -0.60
    makeConstraints
    -0.59
    POSITIVE LOGITS
    SequentialGroup
    0.58
    ddots
    0.53
    RenderAtEndOf
    0.52
    GraphicsUnit
    0.51
    AnchorTagHelper
    0.49
    ParallelGroup
    0.49
     Meksiku
    0.49
    deelte
    0.49
     légitime
    0.49
    principalColumn
    0.48
    Activations Density 3.509%

    No Known Activations