© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1024
    Prev
    Next
    INDEX
    Explanations

    combining wet and dry ingredients

    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_39_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
     подой
    0.34
     Heater
    0.33
     Blink
    0.31
     Shad
    0.31
    oretum
    0.30
    GetBytes
    0.30
    漑
    0.30
    分けて
    0.29
    ikh
    0.29
     heater
    0.29
    POSITIVE LOGITS
     discard
    0.36
    discard
    0.36
     discarding
    0.34
     crim
    0.31
     discarded
    0.31
    Discard
    0.30
    𝘴
    0.29
     jar
    0.29
    सिल
    0.29
     activar
    0.29
    Activations Density 0.293%

    No Known Activations