© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144423
    Prev
    Next
    INDEX
    Explanations

    von + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    م
    1.91
    ن
    1.87
    न
    1.80
    w
    1.73
    ع
    1.69
    ം
    1.65
    li
    1.59
    ق
    1.58
    м
    1.54
    при
    1.51
    POSITIVE LOGITS
     for
    1.77
    ata
    1.27
    ία
    1.27
    )。
    1.27
    .
    1.19
     फॉर
    1.18
    4
    1.17
    ith
    1.16
    ala
    1.13
    oy
    1.09
    Activations Density 0.000%

    No Known Activations