© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36064
    Prev
    Next
    INDEX
    Explanations

    power and electrical connections

    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_31_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
    System
    0.39
    🔼
    0.39
     кален
    0.36
     कांस
    0.36
     Fou
    0.36
    Silver
    0.35
    izowane
    0.35
    システム
    0.35
    ABI
    0.35
    副
    0.35
    POSITIVE LOGITS
    electricity
    0.50
     electricity
    0.46
     tether
    0.44
     wired
    0.42
    電源
    0.41
    电源
    0.41
    nearby
    0.41
     rigging
    0.40
     القدر
    0.40
     Anchor
    0.40
    Activations Density 0.044%

    No Known Activations