© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205542
    Prev
    Next
    INDEX
    Explanations

    statistical variables and experiments

    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_10_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
    ی
    0.55
    ের
    0.50
    s
    0.49
    라
    0.49
    ओं
    0.48
     sprach
    0.47
    </u>
    0.44
    р
    0.41
     Yeshu
    0.41
     Studien
    0.41
    POSITIVE LOGITS
     pairwise
    0.43
    надцать
    0.41
     被
    0.40
     reap
    0.38
     bằng
    0.38
    ཎ
    0.38
    <0xAC>
    0.38
    trt
    0.37
    ﻑ
    0.35
     insecticide
    0.35
    Activations Density 0.040%

    No Known Activations