© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2429
    Prev
    Next
    INDEX
    Explanations

    Persistent storage (EBS, volumes, disk)

    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_40_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
    strument
    0.37
    Swe
    0.37
    arbeitung
    0.36
    ttle
    0.36
    Banking
    0.35
    Taking
    0.35
     Swe
    0.34
    从未
    0.34
    ゅ
    0.34
    toolkit
    0.33
    POSITIVE LOGITS
     Persistent
    0.56
     persistent
    0.54
    Persistent
    0.54
    persistent
    0.46
     EBS
    0.46
     RBD
    0.46
     Ebony
    0.44
     Premium
    0.42
    Premium
    0.41
     Pers
    0.41
    Activations Density 0.011%

    No Known Activations