© 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. 161399
    Prev
    Next
    INDEX
    Explanations

    long-term horizon

    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
     Earnings
    0.39
    Earnings
    0.37
     earnings
    0.36
     ধারাবাহিক
    0.36
    摄像
    0.36
     BUILDING
    0.35
     مسلسل
    0.35
    earnings
    0.35
    迤
    0.35
     suf
    0.34
    POSITIVE LOGITS
    անակ
    0.40
    ñas
    0.40
    cartes
    0.39
    SRPS
    0.39
    FullPath
    0.39
     elast
    0.38
     Treatments
    0.38
    တယ်
    0.37
    reat
    0.36
    agées
    0.36
    Activations Density 0.007%

    No Known Activations