© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128921
    Prev
    Next
    INDEX
    Explanations

    WDF, VoLTE, yuppie

    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_6_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
    ం
    0.89
     (
    0.84
    ى
    0.83
    ление
    0.81
    ного
    0.81
    ↵↵
    0.79
    ين
    0.79
    kannya
    0.78
    м
    0.78
    م
    0.77
    POSITIVE LOGITS
    ტ
    1.14
    i
    1.02
    }$.
    0.98
    a
    0.92
     juvenil
    0.90
    ED
    0.87
    c
    0.86
     サイズ
    0.83
     Neend
    0.81
    NASDAQ
    0.80
    Activations Density 0.000%

    No Known Activations