© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3083
    Prev
    Next
    INDEX
    Explanations

    motion planning

    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_39_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
    LLER
    0.40
     ANIM
    0.39
    ENERGY
    0.37
    毉
    0.37
     تد
    0.37
    ANIM
    0.37
     WILD
    0.36
    wild
    0.36
    ::$
    0.36
     eventdata
    0.36
    POSITIVE LOGITS
     planner
    0.51
     planning
    0.47
    planning
    0.44
     Planning
    0.44
    Planning
    0.43
     fusion
    0.42
     congest
    0.42
     Planner
    0.41
     planners
    0.41
     fusing
    0.40
    Activations Density 0.085%

    No Known Activations