© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138064
    Prev
    Next
    INDEX
    Explanations

    power steering and EPS

    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_12_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
    UnityEngine
    0.47
     मकान
    0.46
     Waugh
    0.45
    Насе
    0.45
     petróleo
    0.44
    Houses
    0.44
    溆
    0.44
    Daten
    0.44
     carapace
    0.44
    Slate
    0.43
    POSITIVE LOGITS
     kannst
    0.62
    你可以
    0.57
     השני
    0.56
     midfield
    0.55
     druga
    0.55
     يمكنك
    0.54
     দ্বিতীয়
    0.52
     i
    0.52
     friendship
    0.52
     dos
    0.51
    Activations Density 0.000%

    No Known Activations