© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10914
    Prev
    Next
    INDEX
    Explanations

    words heavily used in conversations in French

    oai_token-act-pair · gemini-2.0-flash

    French chat logs

    np_max-act-logits · gemini-2.0-flash

    say "French words"

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     PhpStorm
    -0.51
    GeneratedValue
    -0.50
     yhte
    -0.47
     Gage
    -0.47
     mina
    -0.46
     dam
    -0.46
    rhosis
    -0.46
    Corner
    -0.46
     Garnett
    -0.46
     Corner
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.71
     stiefel
    0.57
     iconTwitter
    0.54
    MigrationBuilder
    0.54
     Krä
    0.54
     الحره
    0.53
    +#+#
    0.52
     prochaine
    0.52
     otomatig
    0.52
    İstinadlar
    0.51
    Activations Density 0.690%

    No Known Activations