© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174750
    Prev
    Next
    INDEX
    Explanations

    potential for success

    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_24_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
     puffs
    0.23
     мони
    0.20
    যু
    0.20
    Qualified
    0.20
     monk
    0.20
    ሞ
    0.20
    SHORT
    0.20
    ուն
    0.20
     pipes
    0.19
    ترل
    0.19
    POSITIVE LOGITS
     obsess
    0.23
     evident
    0.22
     desg
    0.22
     orthogonal
    0.22
    ismatch
    0.22
     मंगल
    0.21
    orthogonal
    0.21
     सेलिब्र
    0.20
    趋
    0.20
    形势
    0.20
    Activations Density 0.022%

    No Known Activations