© 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. 200039
    Prev
    Next
    INDEX
    Explanations

    Empty data errors

    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
    めた
    0.37
     porches
    0.37
     branca
    0.36
    rk
    0.36
    夜
    0.36
     Institutes
    0.34
     Programmer
    0.34
     eixo
    0.34
    뉴
    0.34
     Yukon
    0.34
    POSITIVE LOGITS
    lien
    0.38
     такое
    0.38
     данные
    0.37
     systém
    0.35
     ስርዓ
    0.35
     सरिया
    0.35
    Duel
    0.35
    Change
    0.35
    мень
    0.35
     système
    0.34
    Activations Density 0.000%

    No Known Activations