© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155578
    Prev
    Next
    INDEX
    Explanations

    right

    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_50_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
    clear
    0.39
    برد
    0.38
    峻
    0.38
    saves
    0.37
    僭
    0.37
    निम्
    0.37
    佚
    0.36
     ব্যপারে
    0.36
    გრ
    0.34
    fertil
    0.34
    POSITIVE LOGITS
     right
    2.72
    right
    2.22
     Right
    2.13
    Right
    2.09
     RIGHT
    2.02
    右
    1.78
     право
    1.71
    RIGHT
    1.66
     右
    1.56
     oike
    1.55
    Activations Density 0.000%

    No Known Activations