© 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. 78294
    Prev
    Next
    INDEX
    Explanations

    morning greetings and possessives

    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
    DEA
    0.38
    ayon
    0.37
    тору
    0.37
     preponderance
    0.36
    깡
    0.36
     препо
    0.36
    akey
    0.36
    葯
    0.35
    补充
    0.35
     mnogo
    0.35
    POSITIVE LOGITS
     acompanhar
    0.39
     オフィス
    0.36
     accomp
    0.35
    accomp
    0.35
     accompanied
    0.35
     solvents
    0.35
    モーニング
    0.34
     bijective
    0.34
     landsc
    0.34
    Office
    0.34
    Activations Density 0.041%

    No Known Activations