© 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. 5840
    Prev
    Next
    INDEX
    Explanations

    Fisherman's Bastion,curvature

    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
     म्हट
    1.11
     نامه
    0.97
    ❞
    0.94
     cài
    0.93
    <0xF1>
    0.91
    Кто
    0.90
    ність
    0.90
     concerted
    0.89
    Ngoài
    0.88
    Doch
    0.87
    POSITIVE LOGITS
    tagName
    1.06
    φη
    1.05
    ри
    0.99
    гка
    0.98
    вани
    0.97
    ্স
    0.96
    ुम
    0.95
     nrow
    0.95
     byteArray
    0.95
    𝐟
    0.94
    Activations Density 0.006%

    No Known Activations