© 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. 15170
    Prev
    Next
    INDEX
    Explanations

    technical writing and transitions, especially the word "example"

    oai_token-act-pair · gemini-2.0-flash

    example

    np_max-act · gemini-2.0-flash

    ▁example

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ↵↵
    -1.50
    .
    -1.32
    ↵
    -1.27
    <eos>
    -1.10
     
    -1.07
     (
    -1.06
     A
    -0.97
      
    -0.95
     The
    -0.93
    '
    -0.91
    POSITIVE LOGITS
     Efq
    2.08
     myſelf
    1.96
     Theſe
    1.91
     ſeveral
    1.88
     itſelf
    1.87
     Jefus
    1.84
     Monfieur
    1.82
     Reſ
    1.77
     whoſe
    1.75
     Houſe
    1.73
    Activations Density 3.277%

    No Known Activations