© 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. 24833
    Prev
    Next
    INDEX
    Explanations

    sc

    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
     scratch
    0.77
     scratched
    0.70
     scratching
    0.66
    scratch
    0.62
     scratches
    0.59
     Scratch
    0.54
     scrapping
    0.38
    entiti
    0.37
    śla
    0.37
    썰
    0.37
    POSITIVE LOGITS
     Sc
    2.84
    sc
    2.59
    Sc
    2.41
     sc
    2.36
     scap
    1.16
     scallops
    1.09
     SC
    1.08
     scab
    1.07
     scut
    1.05
     scallop
    1.03
    Activations Density 0.085%

    No Known Activations