© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167650
    Prev
    Next
    INDEX
    Explanations

    size of the universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    ीय
    0.42
     sized
    0.39
    sized
    0.37
     کھیلتے
    0.36
    ‘
    0.36
     lớn
    0.35
     крупные
    0.35
     பெரிய
    0.35
    cups
    0.34
    寇
    0.34
    POSITIVE LOGITS
    riere
    0.43
     Ma
    0.42
     Mo
    0.40
     ani
    0.40
     mencegah
    0.40
     Moch
    0.40
     Obr
    0.39
     Ani
    0.39
     جل
    0.38
    នូវ
    0.38
    Activations Density 0.018%

    No Known Activations