© 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. 30422
    Prev
    Next
    INDEX
    Explanations

    effectiveness and limitations

    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
    Negative Logits
    ഴ
    0.40
     predicting
    0.39
    预测
    0.39
    考試
    0.38
     भारी
    0.37
    ulnerability
    0.37
     predict
    0.37
    刮
    0.36
    AID
    0.36
    Ӹ
    0.36
    POSITIVE LOGITS
     reworking
    0.51
     reworked
    0.42
     এদিকে
    0.40
     rework
    0.40
     rearranged
    0.39
     Condensed
    0.37
     rearrangement
    0.37
     rearrangements
    0.37
     Dude
    0.36
     reorganize
    0.36
    Activations Density 0.015%

    No Known Activations