© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63959
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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_46_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
     우리는
    0.43
    توا
    0.41
     exced
    0.40
    Merk
    0.39
    ষ
    0.37
    قص
    0.37
    फ
    0.37
    彥
    0.36
     referenced
    0.36
     সিল
    0.36
    POSITIVE LOGITS
     thoroughly
    0.43
     hold
    0.39
    持有
    0.38
    hold
    0.38
     held
    0.38
     holdings
    0.38
     halten
    0.37
    DropDownItem
    0.37
    держи
    0.37
     Thorough
    0.36
    Activations Density 0.000%

    No Known Activations