© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193417
    Prev
    Next
    INDEX
    Explanations

    that the

    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_27_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
     shì
    0.42
     कुर्बानी
    0.38
    ⍵
    0.38
    fitri
    0.38
    PRET
    0.38
    דר
    0.37
     nhiêu
    0.37
    衍
    0.37
     شرح
    0.36
    ธอ
    0.36
    POSITIVE LOGITS
    leyball
    0.40
     ceases
    0.39
     znajduje
    0.39
    umna
    0.38
     znajdu
    0.38
    ravés
    0.38
    forschung
    0.38
     fleurs
    0.38
     tutaj
    0.38
    umni
    0.38
    Activations Density 0.001%

    No Known Activations