© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1692
    Prev
    Next
    INDEX
    Explanations

    Singapore

    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_44_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
     ऑपरेट
    0.38
    :(
    0.37
    міністра
    0.36
     overcome
    0.36
     oper
    0.35
    NF
    0.35
    폰
    0.35
     ché
    0.35
    ठी
    0.35
    NS
    0.35
    POSITIVE LOGITS
     заканчи
    0.39
    bus
    0.38
    Quiz
    0.38
    quiz
    0.37
    वियस
    0.37
     octagon
    0.37
    芴
    0.36
     क्रिया
    0.36
    textwidth
    0.36
    ynchus
    0.36
    Activations Density 0.038%

    No Known Activations