© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216178
    Prev
    Next
    INDEX
    Explanations

    Saf

    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_47_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
     bureaucratic
    0.43
     expire
    0.41
     passé
    0.41
    遍
    0.41
    dé
    0.39
     pass
    0.38
     Neu
    0.38
     Ali
    0.38
     ha
    0.37
     fab
    0.37
    POSITIVE LOGITS
     пом
    0.41
    バター
    0.39
    Ⴖ
    0.38
    (!
    0.38
    ---+
    0.37
    ობა
    0.37
    ---
    0.37
    ิลป
    0.36
     Elsie
    0.36
     تكعيب
    0.36
    Activations Density 0.001%

    No Known Activations