© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195977
    Prev
    Next
    INDEX
    Explanations

    space ships

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ships
    2.00
    船
    1.94
     кораб
    1.92
     ship
    1.84
     Ships
    1.78
     boat
    1.75
     boats
    1.74
    เรือ
    1.69
     জাহাজ
    1.63
    Ships
    1.63
    POSITIVE LOGITS
    heide
    0.38
     मश
    0.36
    IPO
    0.36
     Bour
    0.35
     मिरची
    0.35
    🐛
    0.34
     Blanket
    0.33
    鹑
    0.33
    喤
    0.33
     Теннис
    0.33
    Activations Density 0.006%

    No Known Activations