© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143542
    Prev
    Next
    INDEX
    Explanations

    programming

    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_46_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
    oster
    0.40
     match
    0.39
    zs
    0.38
    рук
    0.36
     exceptional
    0.36
    Remark
    0.35
    Following
    0.35
    remarkable
    0.35
     use
    0.35
    [$
    0.35
    POSITIVE LOGITS
     Тыва
    0.45
     μας
    0.42
    𒈾
    0.41
    ్రహ
    0.40
    ﮄ
    0.40
     }%
    0.39
     непотпуним
    0.39
     बेंगल
    0.39
     AGAIN
    0.38
     conmigo
    0.38
    Activations Density 0.031%

    No Known Activations