© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254191
    Prev
    Next
    INDEX
    Explanations

    self

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    %)
    0.39
    )");
    0.39
     الحالة
    0.39
    付近
    0.36
    ဖြင့်
    0.35
     concentrated
    0.35
    ﻦ
    0.35
     douceur
    0.34
    닿
    0.34
     টাইমস
    0.33
    POSITIVE LOGITS
    !!.
    0.66
    .__
    0.59
    .$.
    0.56
    ?.
    0.54
    。.
    0.52
    ؟.
    0.52
    ​.
    0.52
    .#
    0.51
    ।.
    0.50
    !.
    0.50
    Activations Density 0.006%

    No Known Activations