© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257375
    Prev
    Next
    INDEX
    Explanations

    is my

    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_22_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
    ряд
    0.37
     вещества
    0.35
    ʖ
    0.35
    拴
    0.35
     Ghanaian
    0.34
    രംഭ
    0.34
     charcoal
    0.34
    Эк
    0.34
    缕
    0.34
    掳
    0.34
    POSITIVE LOGITS
    ronique
    0.40
     YOUR
    0.39
    YOUR
    0.39
     Costello
    0.38
    メール
    0.37
     ਤੁਹਾ
    0.37
     やっぱり
    0.37
    フジ
    0.37
     Hase
    0.37
     Russell
    0.36
    Activations Density 0.000%

    No Known Activations