© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11304
    Prev
    Next
    INDEX
    Explanations

    robotic arm manipulation and 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_13_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
    ждение
    0.51
    Ⲇ
    0.46
    effer
    0.46
     dyeing
    0.46
    ственное
    0.45
    ěž
    0.45
     Много
    0.45
     Dyed
    0.45
    érm
    0.44
    enderal
    0.44
    POSITIVE LOGITS
    ensioni
    0.49
    بي
    0.47
     Italy
    0.47
     embarazo
    0.46
    Italy
    0.46
     BU
    0.46
    %\
    0.46
    রোপ
    0.45
     برش
    0.45
     حوالي
    0.44
    Activations Density 0.033%

    No Known Activations