© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196643
    Prev
    Next
    INDEX
    Explanations

    nearest/closest ancestor

    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_27_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
     arteries
    0.43
    хим
    0.43
     quarts
    0.40
    सर्जन
    0.39
     stoves
    0.39
     subgoal
    0.39
    🐴
    0.39
     watering
    0.38
     Criterion
    0.38
     irrigation
    0.38
    POSITIVE LOGITS
     pelajaran
    0.36
    license
    0.36
    Results
    0.36
    最终
    0.36
     шан
    0.36
    chance
    0.36
    untansi
    0.36
    gebnisse
    0.35
    敢
    0.35
    回报
    0.35
    Activations Density 0.001%

    No Known Activations