© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    capitalized words and common abbreviations

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
     <=",
    -1.02
     pinulongan
    -0.99
    oa̍t
    -0.96
     surla
    -0.94
    InputBorder
    -0.92
     تضيفلها
    -0.91
    ConstraintMaker
    -0.88
     snippetHide
    -0.87
    __":
    -0.87
    Autoritní
    -0.86
    POSITIVE LOGITS
    '
    1.59
    ’
    1.48
    `
    0.81
    ´
    0.78
    ′
    0.75
    ''
    0.71
    ʻ
    0.68
    \'
    0.68
    ‘
    0.68
    ʼ
    0.65
    Activations Density 1.656%

    No Known Activations