© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15627
    Prev
    Next
    INDEX
    Explanations

    code snippets containing brackets, letters, numbers, and the word "above"

    oai_token-act-pair · gemini-2.0-flash

    code or markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ↵↵
    -0.42
    ↵
    -0.37
    Association
    -0.36
    ...
    -0.34
    あり
    -0.33
    .
    -0.33
    ker
    -0.33
    哋
    -0.33
    …
    -0.31
     Association
    -0.31
    POSITIVE LOGITS
    +#+#
    1.09
    parsedMessage
    0.99
    出版年
    0.91
    expandindo
    0.91
    AddTagHelper
    0.90
    MessageOf
    0.90
    sizeCache
    0.89
    LookAnd
    0.88
     estimés
    0.86
     виправивши
    0.85
    Activations Density 45.723%

    No Known Activations