© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200684
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    는
    0.96
    ων
    0.83
    O
    0.82
    적인
    0.81
    ăți
    0.81
     plausible
    0.79
     standstill
    0.79
    ﻓ
    0.79
    ﺄ
    0.79
    ならない
    0.78
    POSITIVE LOGITS
     to
    1.52
    {
    1.19
     on
    1.08
    ف
    1.05
    ল
    0.96
     and
    0.92
    \
    0.91
    ری
    0.88
     it
    0.88
     lanç
    0.88
    Activations Density 0.000%

    No Known Activations