© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215469
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    ро
    1.45
    0
    1.38
    ли
    1.32
    1.28
    _
    1.24
    1
    1.23
    not
    1.22
     писа
    1.18
    لا
    1.12
    I
    1.10
    POSITIVE LOGITS
     to
    1.26
     ilmu
    1.05
     spp
    1.03
     titt
    1.02
     you
    0.99
     of
    0.97
     beri
    0.96
     outro
    0.95
     arctic
    0.92
    ب
    0.92
    Activations Density 0.000%

    No Known Activations