© 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. 199918
    Prev
    Next
    INDEX
    Explanations

    offense or attack, and its force or struggles

    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
     whence
    0.36
     méxico
    0.35
     interdiscipl
    0.35
     ope
    0.35
     konfl
    0.34
     alle
    0.34
     nep
    0.33
     ଓ
    0.33
     ziel
    0.32
     atyp
    0.32
    POSITIVE LOGITS
    Houses
    0.39
    घर
    0.39
     घर
    0.38
     Houses
    0.37
    House
    0.37
     houses
    0.36
     तुम्ही
    0.36
    Grunge
    0.35
    집
    0.34
    Ability
    0.34
    Activations Density 0.001%

    No Known Activations