© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4431
    Prev
    Next
    INDEX
    Explanations

    trim level

    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_40_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
     convertible
    0.41
    বৈ
    0.41
     販売
    0.40
    ше
    0.39
    வு
    0.39
     racing
    0.38
     éd
    0.38
    輌
    0.38
    Racing
    0.38
    转化为
    0.38
    POSITIVE LOGITS
     outside
    0.42
     Outside
    0.38
    Outside
    0.38
     dehors
    0.37
     Fashion
    0.37
     নিষ্ঠ
    0.37
     प्रिंस
    0.37
     Kiss
    0.36
    outside
    0.36
     밖에
    0.35
    Activations Density 0.048%

    No Known Activations