© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228575
    Prev
    Next
    INDEX
    Explanations

    Mal

    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_57_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
    褲
    0.40
    सरी
    0.38
     supervisory
    0.37
     পর
    0.37
    VEN
    0.37
     Achieving
    0.37
    kovskij
    0.36
     desen
    0.36
     Abdul
    0.35
     นับ
    0.35
    POSITIVE LOGITS
    mies
    0.46
     y
    0.45
     پی
    0.44
     Yas
    0.43
     piy
    0.43
    ຍ
    0.43
    yas
    0.42
    ाया
    0.42
     пі
    0.41
    aya
    0.41
    Activations Density 0.000%

    No Known Activations