© 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. 249433
    Prev
    Next
    INDEX
    Explanations

    luck, unique

    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
    पति
    0.37
    昻
    0.36
    Keeper
    0.36
    arding
    0.35
     Bug
    0.35
     ас
    0.35
    Fx
    0.35
    ashing
    0.34
    カップ
    0.34
    ミル
    0.34
    POSITIVE LOGITS
    独
    0.63
    运
    0.60
     운
    0.55
    運
    0.54
    青
    0.48
    獨
    0.44
    청
    0.44
     vận
    0.43
     luck
    0.42
    靑
    0.42
    Activations Density 0.000%

    No Known Activations