© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113217
    Prev
    Next
    INDEX
    Explanations

    focused on

    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_2_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
    માં
    2.09
     to
    1.71
     that
    1.65
    на
    1.43
    ના
    1.40
    ные
    1.34
    that
    1.32
    ା
    1.31
    That
    1.27
    quela
    1.27
    POSITIVE LOGITS
     K
    1.18
     U
    1.16
     D
    1.04
     L
    1.03
     B
    1.01
     S
    0.98
     A
    0.95
     The
    0.94
     M
    0.93
     V
    0.92
    Activations Density 0.001%

    No Known Activations