© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13952
    Prev
    Next
    INDEX
    Explanations

    French contractions preceded by letters

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    np_max-act-logits · gemini-2.0-flash

    apostrophe (’)

    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
     betweenstory
    -0.58
    >",
    -0.49
       
    -0.47
     isNameExpr
    -0.46
     ?',
    -0.45
    dressing
    -0.45
     sifted
    -0.44
    ?>">
    -0.44
    ?>"
    -0.44
    "]]
    -0.43
    POSITIVE LOGITS
    Amérique
    0.78
    escalier
    0.76
    enfance
    0.76
    Egypte
    0.75
    amitié
    0.75
    Empereur
    0.73
    abbaye
    0.73
    Égypte
    0.72
    empereur
    0.71
    Irlande
    0.71
    Activations Density 1.343%

    No Known Activations