© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    ellipses and the word "read", likely as indicators of article snippets

    oai_token-act-pair · gemini-2.0-flash

    Blog article snippet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.94
     
    -0.83
      
    -0.83
     B
    -0.81
     a
    -0.77
     M
    -0.75
     les
    -0.73
     E
    -0.73
     H
    -0.70
     J
    -0.70
    POSITIVE LOGITS
     Efq
    1.39
     Majefty
    1.30
     Monfieur
    1.21
     Shakspeare
    1.17
     myſelf
    1.17
     houſe
    1.16
     $_"
    1.16
     photolibrary
    1.15
     pleaſure
    1.15
     Houſe
    1.13
    Activations Density 0.821%

    No Known Activations