© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254102
    Prev
    Next
    INDEX
    Explanations

    thread

    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_56_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
     ಸುತ್ತ
    0.40
    ⱨ
    0.40
    substantial
    0.40
     ඔබ
    0.39
    built
    0.38
     /(\
    0.37
    LARGE
    0.37
     /
    0.36
    هو
    0.36
    HEY
    0.35
    POSITIVE LOGITS
     complaining
    0.57
     calling
    0.57
     speaking
    0.54
     Calling
    0.53
     replying
    0.52
     criticizing
    0.49
     announcing
    0.48
     answering
    0.47
     administering
    0.47
     importing
    0.47
    Activations Density 0.001%

    No Known Activations