© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5642
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "equals"

    oai_token-act-pair · gemini-2.0-flash

    equals

    np_max-act · gemini-2.0-flash

    equals Method used: 1 — reason: identical MAX_ACTIVATING_TOKENS — explanation: equals

    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
    ...
    -0.88
    <eos>
    -0.88
     O
    -0.85
     (
    -0.79
    ,
    -0.79
     N
    -0.78
     G
    -0.78
     F
    -0.77
    ↵
    -0.76
     A
    -0.73
    POSITIVE LOGITS
     myſelf
    1.91
     Efq
    1.77
     purpoſe
    1.72
     Monfieur
    1.67
     Theſe
    1.61
     pleaſure
    1.59
     houſe
    1.58
     faſt
    1.52
     itſelf
    1.52
     ſtate
    1.52
    Activations Density 2.191%

    No Known Activations