© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2954
    Prev
    Next
    INDEX
    Explanations

    French language and words often used in messaging or coding contexts.

    oai_token-act-pair · gemini-2.0-flash

    Chat messages

    np_max-act · 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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.62
     nous
    -0.51
    सन्दर्भ
    -0.41
    reactivex
    -0.41
    laması
    -0.40
     maso
    -0.40
     gå
    -0.40
    Население
    -0.40
     ro
    -0.40
     actually
    -0.39
    POSITIVE LOGITS
    twimg
    0.75
    Viited
    0.71
     насељу
    0.71
    DoubleQuotes
    0.71
    GraphicsUnit
    0.70
     Seeder
    0.69
    aarrggbb
    0.69
    setupUi
    0.67
    bootstrapcdn
    0.67
     समीक्षाएं
    0.67
    Activations Density 5.616%

    No Known Activations