© 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. 6419
    Prev
    Next
    INDEX
    Explanations

    a lot of random punctuation and numbers, plus the word "info"

    oai_token-act-pair · gemini-2.0-flash

    punctuation and common sentence starters

    np_token-act-pair-logits · gpt-4o-mini
    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
    parsedMessage
    -0.93
     متعلقه
    -0.84
     itſelf
    -0.83
    
    -0.82
    ########.
    -0.82
     betweenstory
    -0.81
    RenderAtEndOf
    -0.81
    <unused6>
    -0.79
    <unused1>
    -0.79
    <pad>
    -0.78
    POSITIVE LOGITS
     
    0.57
     the
    0.55
     (
    0.50
     in
    0.46
     that
    0.45
     a
    0.44
     "
    0.44
    ,
    0.43
    .
    0.43
     on
    0.43
    Activations Density 1.948%

    No Known Activations