© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242058
    Prev
    Next
    INDEX
    Explanations

    unanimous or overwhelming approval

    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_25_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
     Carre
    0.41
     पोप
    0.41
     inactive
    0.41
     trendy
    0.39
     पुराने
    0.39
    ère
    0.38
     pouvoir
    0.37
    ępu
    0.37
    रुख
    0.36
    ))=\
    0.36
    POSITIVE LOGITS
     recoveries
    0.48
     understandings
    0.46
     imprese
    0.41
     fatalities
    0.40
     behaviors
    0.39
    voll
    0.38
     hervorrag
    0.38
     violations
    0.38
    violations
    0.38
     alumina
    0.38
    Activations Density 0.000%

    No Known Activations