© 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. 77776
    Prev
    Next
    INDEX
    Explanations

    meaning I

    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
     crop
    0.37
     σ
    0.34
     ότι
    0.34
     exclu
    0.33
     Crop
    0.33
    ستا
    0.32
     obe
    0.32
    IEN
    0.32
    袭
    0.32
     sog
    0.31
    POSITIVE LOGITS
    人们
    0.34
    Stanley
    0.34
    жнарод
    0.33
    බැ
    0.32
     steepest
    0.32
     যাঁ
    0.31
    人們
    0.31
     Stanley
    0.31
    inalis
    0.31
     }{}_{\
    0.31
    Activations Density 0.012%

    No Known Activations