© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139014
    Prev
    Next
    INDEX
    Explanations

    blue, deep water, light absorption

    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_12_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
    ANIA
    0.55
    ﺔ
    0.53
     refurbishment
    0.51
    انے
    0.49
     revitalization
    0.49
    YER
    0.49
    Dopo
    0.48
    Ż
    0.48
     repair
    0.48
    WARE
    0.48
    POSITIVE LOGITS
    ak
    0.56
    ou
    0.48
    w
    0.46
    asser
    0.44
    ab
    0.44
    ac
    0.44
     Fake
    0.43
     ฟ้า
    0.42
    ul
    0.42
    og
    0.42
    Activations Density 0.002%

    No Known Activations