© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    climbing structures or furniture

    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
    eiro
    0.35
     आधी
    0.34
    hitva
    0.33
    liang
    0.33
    活跃
    0.31
    fields
    0.31
    ("/
    0.31
     ০১
    0.31
     hatt
    0.30
    rogate
    0.30
    POSITIVE LOGITS
     Freezer
    0.48
     refrigerators
    0.47
     freezer
    0.45
     refrigerator
    0.42
     vehicles
    0.41
     дра
    0.40
     холоди
    0.39
     Refriger
    0.38
    冰箱
    0.38
     boats
    0.37
    Activations Density 0.106%

    No Known Activations