© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 6132
    Prev
    Next
    INDEX
    Explanations

    anime characters and fantasy settings

    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_38_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
    েশ
    0.42
     ʼ
    0.39
     ('
    0.38
    箋
    0.38
     бом
    0.38
    舂
    0.38
    CheckingType
    0.37
    擀
    0.37
    ciphertext
    0.37
     funcionalidad
    0.37
    POSITIVE LOGITS
     holy
    0.47
     Merlin
    0.41
    Rough
    0.38
     पवित्र
    0.38
     esc
    0.38
    holy
    0.38
    Long
    0.37
     Peers
    0.37
     Muc
    0.37
     enchanted
    0.37
    Activations Density 0.025%

    No Known Activations