© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194767
    Prev
    Next
    INDEX
    Explanations

    (

    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_50_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
     powiat
    0.40
    Jerry
    0.38
     jinfo
    0.37
     relem
    0.37
     Jerry
    0.36
    াইতে
    0.36
    Entertainment
    0.36
     आसार
    0.36
    욱
    0.35
    醤
    0.35
    POSITIVE LOGITS
     confront
    0.46
     corrupted
    0.41
     Coron
    0.40
    ウェ
    0.39
     cardio
    0.39
     MCS
    0.39
    urkan
    0.38
     espress
    0.38
     Qf
    0.38
    QM
    0.37
    Activations Density 0.000%

    No Known Activations