© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195734
    Prev
    Next
    INDEX
    Explanations

    dive or aircraft actions

    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
    рел
    0.55
    Rack
    0.53
    ुरू
    0.52
     банка
    0.52
     संतुलित
    0.52
    ن
    0.52
    During
    0.51
     банков
    0.51
     प्रवा
    0.51
     связаны
    0.51
    POSITIVE LOGITS
     '
    0.52
    lar
    0.52
     illumination
    0.52
     Z
    0.51
     z
    0.50
     besta
    0.49
     McCullough
    0.49
     "
    0.49
     A
    0.48
     bizarre
    0.48
    Activations Density 0.000%

    No Known Activations