© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215167
    Prev
    Next
    INDEX
    Explanations

    impressed with the team's

    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_31_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
    oad
    0.41
    充
    0.36
    </a>
    0.36
    pha
    0.35
    dichloro
    0.35
    чатки
    0.35
    }}$
    0.34
    TRAN
    0.34
     clav
    0.34
    찔
    0.34
    POSITIVE LOGITS
    ീകരണ
    0.41
     सर
    0.40
     божо
    0.39
     वा
    0.39
     তারাও
    0.38
     সাহেবের
    0.37
     IERC
    0.37
     empe
    0.37
     Counseling
    0.37
     vm
    0.37
    Activations Density 0.001%

    No Known Activations