© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11628
    Prev
    Next
    INDEX
    Explanations

    French contractions and hyphenated words

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    np_max-act-logits · gemini-2.0-flash

    ' Method used: 1 — all max tokens are apostrophes — '

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     A
    -0.49
     Italijani
    -0.49
    RenderAtEndOf
    -0.47
    UnusedPrivate
    -0.45
     illetve
    -0.43
    IALE
    -0.43
    MemoryWarning
    -0.43
    ьогодні
    -0.42
     ab
    -0.42
     O
    -0.40
    POSITIVE LOGITS
    empêcher
    0.93
     Houſe
    0.83
    élimin
    0.77
    améli
    0.75
    égard
    0.73
    extré
    0.71
    éviter
    0.71
     myſelf
    0.70
    atteindre
    0.69
     Breed
    0.69
    Activations Density 1.549%

    No Known Activations