© 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. 74620
    Prev
    Next
    INDEX
    Explanations

    So followed by an imperative

    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
     Catalina
    0.40
    সল
    0.38
    Catal
    0.38
    コリ
    0.37
     Salt
    0.37
    Salt
    0.36
    িত্তিক
    0.35
     Katal
    0.35
    🔄
    0.35
    stationary
    0.35
    POSITIVE LOGITS
     amazingly
    0.42
    idée
    0.40
    pré
    0.39
    geg
    0.39
    क्योंकि
    0.39
    ség
    0.37
    liu
    0.37
    ligen
    0.37
     सौंदर्य
    0.37
    آن
    0.36
    Activations Density 0.000%

    No Known Activations