© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157833
    Prev
    Next
    INDEX
    Explanations

    AR/AP prefixes

    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_2_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
    の後
    1.08
    ின்
    1.05
    のための
    1.05
    తో
    1.02
    的气
    1.01
    та
    1.00
              
    0.98
    ﻛ
    0.98
     fashioned
    0.98
     އަ
    0.98
    POSITIVE LOGITS
    an
    1.91
    ne
    1.86
    ?
    1.68
    ان
    1.61
    ری
    1.41
    ط
    1.41
    m
    1.40
    ่
    1.38
    م
    1.37
    не
    1.31
    Activations Density 0.000%

    No Known Activations