© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    housing and comfort

    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
     Elements
    0.40
     Bootstrap
    0.39
     elements
    0.39
     histories
    0.38
    滩
    0.38
    Elements
    0.37
     guiclass
    0.37
    พื้นที่
    0.36
     உயிர
    0.36
     भाषाओं
    0.36
    POSITIVE LOGITS
     commod
    0.55
    舒适
    0.49
     magnificence
    0.44
    舒服
    0.44
    宫
    0.44
     bequem
    0.43
    commod
    0.42
    Intersect
    0.42
    comfortable
    0.41
     удоб
    0.40
    Activations Density 0.021%

    No Known Activations