© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2961
    Prev
    Next
    INDEX
    Explanations

    building user interfaces

    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
     liquors
    0.39
    模
    0.38
    solutions
    0.36
     lash
    0.36
    pageX
    0.36
     ବି
    0.36
     kär
    0.35
     solutions
    0.35
     lashes
    0.35
    解决方案
    0.34
    POSITIVE LOGITS
    USER
    0.43
    User
    0.40
    单
    0.40
    user
    0.40
     SINGLE
    0.39
     सिंगल
    0.39
     single
    0.39
     Single
    0.38
    ኖች
    0.38
    Single
    0.38
    Activations Density 0.012%

    No Known Activations