© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    ruby `do` loops

    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
    ן
    3.20
    siniz
    3.04
    न
    3.01
    رین
    2.98
    น
    2.96
    er
    2.79
    ل
    2.77
    น้อง
    2.76
    ness
    2.74
    ל
    2.73
    POSITIVE LOGITS
    ی
    3.05
    fitting
    2.96
    i
    2.83
     backgroundColor
    2.71
     biện
    2.67
    ک
    2.57
    การ
    2.55
     jangan
    2.53
    isr
    2.51
    െ
    2.48
    Activations Density 0.004%

    No Known Activations