© 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. 231587
    Prev
    Next
    INDEX
    Explanations

    Standard Operating Procedures (SOPs)

    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
    Not in Any Lists

    No Comments

    Negative Logits
    s
    1.31
    ed
    1.11
     for
    1.05
     be
    0.96
     are
    0.90
    um
    0.88
     liar
    0.86
    y
    0.86
     FAQ
    0.84
     rheumatoid
    0.84
    POSITIVE LOGITS
    د
    1.08
    S
    0.95
     ﺍﻟ
    0.93
    وي
    0.93
    い
    0.91
     Мен
    0.90
    مر
    0.88
     ﺍ
    0.88
    し
    0.88
    一股
    0.87
    Activations Density 0.000%

    No Known Activations