© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203641
    Prev
    Next
    INDEX
    Explanations

    depot

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     sheltered
    0.48
     Lun
    0.44
     luncheon
    0.43
    Lun
    0.42
    day
    0.41
    Day
    0.40
    determ
    0.39
    staging
    0.39
     зада
    0.38
     ዕ
    0.38
    POSITIVE LOGITS
     Dep
    1.38
     dep
    1.31
    Dep
    1.30
    dep
    1.26
     DEP
    1.20
     dép
    1.15
    DEP
    1.07
     डि
    0.92
     ڈپ
    0.82
     depolarization
    0.79
    Activations Density 0.000%

    No Known Activations