© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ्स
    0.88
     arou
    0.78
     habido
    0.78
    remely
    0.75
    ста
    0.74
    ර
    0.74
     pyautogui
    0.73
    它
    0.73
    𝖘
    0.72
     اسلامی
    0.72
    POSITIVE LOGITS
     polypeptide
    0.78
    ワード
    0.78
     discontinue
    0.77
    员
    0.77
    seekBar
    0.76
    រី
    0.75
    ка
    0.74
     expres
    0.72
     polypeptides
    0.70
     же
    0.70
    Activations Density 0.122%

    No Known Activations