© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11933
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and numbers in text

    oai_token-act-pair · gemini-2.0-flash

    file extensions and verbal phrases

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    .
    -1.05
    ...
    -0.73
    …
    -0.70
    ,’
    -0.69
    ./
    -0.69
    .'
    -0.69
    . 
    -0.68
    .,
    -0.68
     ***!
    -0.68
    .’
    -0.67
    POSITIVE LOGITS
    com
    0.82
    docx
    0.70
     It
    0.69
    jpg
    0.68
     The
    0.68
     године
    0.67
     This
    0.64
    org
    0.61
     In
    0.59
    COM
    0.59
    Activations Density 13.374%

    No Known Activations