© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249072
    Prev
    Next
    INDEX
    Explanations

    comfortable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    building
    0.41
    coming
    0.40
     ক
    0.40
     p
    0.39
     glad
    0.39
     चाहें
    0.39
     c
    0.38
    computing
    0.38
     к
    0.37
    housing
    0.37
    POSITIVE LOGITS
     Meeting
    0.74
    Meeting
    0.71
     MEETING
    0.69
     meeting
    0.68
    meeting
    0.62
     satisfying
    0.50
     मीटिंग
    0.43
    會
    0.39
    会的
    0.38
    ˣ
    0.37
    Activations Density 0.003%

    No Known Activations