© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62843
    Prev
    Next
    INDEX
    Explanations

    b followed by A or Energy

    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
    Negative Logits
    ية
    1.21
    ين
    1.02
    اسية
    1.00
    ientemente
    0.96
    га
    0.92
    ěru
    0.92
    нику
    0.92
     「
    0.91
    üglich
    0.90
    も
    0.89
    POSITIVE LOGITS
     you
    1.72
     уви
    1.42
     can
    1.40
    3
    1.39
     I
    1.36
    る
    1.34
    ۴
    1.34
    </strong>
    1.33
    1
    1.32
     the
    1.30
    Activations Density 0.000%

    No Known Activations