© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128994
    Prev
    Next
    INDEX
    Explanations

    honesty and integrity

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     powied
    0.90
     )
    0.86
     .)
    0.86
    ?)
    0.81
    <td>
    0.80
    )
    0.80
    ).
    0.78
    ;
    0.77
    .)
    0.77
    W
    0.75
    POSITIVE LOGITS
    های
    0.93
    لی
    0.80
    ಿಯ
    0.79
    기
    0.77
     of
    0.77
    리
    0.77
    ﺸ
    0.73
     결정
    0.73
    ಸ
    0.73
    ಮ
    0.72
    Activations Density 0.001%

    No Known Activations