© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6795
    Prev
    Next
    INDEX
    Explanations

    some French words and/or HTML formatting, especially in chatbot-style dialogue

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    '

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nôtre
    -1.30
     avoient
    -1.23
     fumée
    -1.23
     étoient
    -1.16
     feroit
    -1.16
     enfans
    -1.15
     vôtre
    -1.14
     auroit
    -1.14
     dignité
    -1.14
     bonté
    -1.13
    POSITIVE LOGITS
     kou
    0.29
    п
    0.29
    жо
    0.29
    в
    0.28
     bebe
    0.28
    с
    0.28
     flee
    0.27
     suddenly
    0.27
    ч
    0.27
    мар
    0.26
    Activations Density 2.115%

    No Known Activations