© 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. 217504
    Prev
    Next
    INDEX
    Explanations

    K names

    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
    ger
    0.40
     কর্নেল
    0.37
     ger
    0.37
    melee
    0.37
    скопа
    0.37
    睍
    0.36
     mil
    0.36
     मो
    0.36
     पन
    0.36
     ме
    0.35
    POSITIVE LOGITS
     Keith
    0.91
    Keith
    0.89
     K
    0.58
    キ
    0.54
     KI
    0.52
     Kieran
    0.52
     Kie
    0.50
     Kep
    0.50
    Tom
    0.49
     kie
    0.49
    Activations Density 0.026%

    No Known Activations