© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4778
    Prev
    Next
    INDEX
    Explanations

    on [topic]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ల
    0.85
    ার
    0.83
    mpi
    0.82
    er
    0.78
    ar
    0.77
    ল
    0.75
    mits
    0.75
    h
    0.74
    다
    0.74
    場合
    0.73
    POSITIVE LOGITS
    र्मेंद्र
    0.77
    𝘯
    0.77
    Экс
    0.75
     hablamos
    0.73
     Vk
    0.70
    ⚠️
    0.68
     Coppa
    0.67
    儡
    0.67
     брат
    0.67
    ‣
    0.66
    Activations Density 0.132%

    No Known Activations