© 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. 33461
    Prev
    Next
    INDEX
    Explanations

    corner pieces

    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
     Story
    0.38
    衣
    0.37
     prés
    0.35
     கதை
    0.35
    隧道
    0.35
    丳
    0.35
    ুল
    0.34
    ストーリー
    0.34
     portfolios
    0.34
    िरी
    0.34
    POSITIVE LOGITS
     corner
    0.96
    corner
    0.86
     corners
    0.82
    Corner
    0.81
     Corners
    0.77
    corners
    0.74
     Corner
    0.73
    Corners
    0.68
    角
    0.66
     कोने
    0.63
    Activations Density 0.042%

    No Known Activations