© 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. 170894
    Prev
    Next
    INDEX
    Explanations

    kl cl

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ലേ
    0.41
    ถม
    0.38
     spokoj
    0.37
    Incrementor
    0.35
    ]]->
    0.34
     спокой
    0.34
    findOrFail
    0.34
     BasicContainer
    0.33
    湄
    0.33
     quies
    0.32
    POSITIVE LOGITS
     kl
    2.06
     Kl
    1.57
    Kl
    1.54
    kl
    1.25
     KL
    1.13
    KL
    1.03
     cl
    0.95
     클
    0.94
    클
    0.82
    Cl
    0.79
    Activations Density 0.000%

    No Known Activations