© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33325
    Prev
    Next
    INDEX
    Explanations

    sunlight through the

    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_31_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
     अधिका
    0.37
    瓜
    0.34
     basking
    0.33
     Virtue
    0.33
     virtue
    0.32
     Introduced
    0.32
    シナ
    0.32
    myY
    0.32
     Carolina
    0.32
    义
    0.32
    POSITIVE LOGITS
    雲
    0.39
     portátil
    0.39
    Время
    0.39
     clouds
    0.39
     gaps
    0.38
    Пор
    0.36
     ห
    0.36
     discre
    0.36
     wahr
    0.36
    ዉ
    0.36
    Activations Density 0.018%

    No Known Activations