© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    proper nouns including names, locations, and organizations, possibly with a preference for legal and medical contexts

    oai_token-act-pair · gemini-2.0-flash

    documentation/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    .
    -0.85
    <eos>
    -0.81
    ,
    -0.80
    ↵↵
    -0.76
     (
    -0.76
     
    -0.76
     and
    -0.71
     S
    -0.69
     "
    -0.69
      
    -0.67
    POSITIVE LOGITS
     Majefty
    1.48
     Efq
    1.45
     myſelf
    1.43
     itſelf
    1.37
     Houſe
    1.34
     purpoſe
    1.34
     ſeveral
    1.34
     houſe
    1.33
     فريبيس
    1.31
     Shakspeare
    1.31
    Activations Density 2.954%

    No Known Activations