© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130804
    Prev
    Next
    INDEX
    Explanations

    Gu

    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_50_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
     m
    0.76
     म
    0.71
     м
    0.68
     م
    0.59
     mak
    0.56
     E
    0.53
    Mak
    0.53
    <0xA0>
    0.51
     ম
    0.51
     Mak
    0.51
    POSITIVE LOGITS
     гу
    1.04
     Гу
    1.04
    Gu
    1.01
     gu
    0.98
     गु
    0.96
     Gü
    0.95
    Гу
    0.94
    гу
    0.91
     Gu
    0.90
    gu
    0.88
    Activations Density 0.004%

    No Known Activations