© 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. 6543
    Prev
    Next
    INDEX
    Explanations

    ASSIGN to object

    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
    鞦
    0.40
     Nesta
    0.39
     ಸಂಗೀತ
    0.38
     timezone
    0.37
    ixen
    0.36
     యూని
    0.36
     typu
    0.36
    ༩
    0.36
    快捷
    0.35
     યુ
    0.34
    POSITIVE LOGITS
    Shapes
    0.45
    getObject
    0.40
    绍
    0.39
    shapes
    0.38
    Ratings
    0.37
    shape
    0.37
    Jacques
    0.36
    ereco
    0.36
     shapes
    0.35
    Shape
    0.35
    Activations Density 0.144%

    No Known Activations