© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14837
    Prev
    Next
    INDEX
    Explanations

    optical properties

    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_15_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
    rewards
    0.51
    Rewards
    0.48
    奖励
    0.47
    見
    0.46
    Hoist
    0.46
     sconf
    0.45
    ्या
    0.45
    ھر
    0.44
    お金
    0.43
    seconds
    0.43
    POSITIVE LOGITS
     i
    0.63
     influenza
    0.59
     uncovering
    0.55
     आस्ट्रेलिया
    0.54
     آپ
    0.51
     problemat
    0.51
     flared
    0.49
     ஆர்
    0.49
     नाटक
    0.49
     grav
    0.49
    Activations Density 0.001%

    No Known Activations