© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212746
    Prev
    Next
    INDEX
    Explanations

    code generation and calculation

    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_19_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
     pecahan
    0.22
     বাহ
    0.21
    首歌
    0.21
    ្ល
    0.20
    能量
    0.20
     Barg
    0.20
    គ្នា
    0.20
    ၜ
    0.20
    ដៃ
    0.20
    λει
    0.19
    POSITIVE LOGITS
     principles
    0.23
     non
    0.22
     rivalry
    0.21
    مص
    0.21
    ificazione
    0.20
     post
    0.20
     co
    0.20
     od
    0.20
    کے
    0.20
     rival
    0.20
    Activations Density 0.022%

    No Known Activations