© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122594
    Prev
    Next
    INDEX
    Explanations

    iterating through files line by line

    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_38_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
     stitched
    0.36
     shining
    0.36
     꺼
    0.36
     briefly
    0.35
     그렇
    0.35
     combining
    0.35
    brief
    0.35
     Combining
    0.34
     動
    0.34
    ில்லை
    0.34
    POSITIVE LOGITS
     Blade
    0.39
    utt
    0.38
    pointers
    0.38
    plugin
    0.37
    opl
    0.37
     blade
    0.37
     âg
    0.37
     niz
    0.37
    blade
    0.36
    DEVICE
    0.36
    Activations Density 0.001%

    No Known Activations