© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237081
    Prev
    Next
    INDEX
    Explanations

    distribution

    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_46_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
     bursting
    0.38
    焖
    0.38
     tea
    0.38
     হইয়াছে
    0.37
     capsule
    0.35
    ษย์
    0.35
    찻
    0.35
    SuspendLayout
    0.34
     ಅಂಶ
    0.34
    賤
    0.34
    POSITIVE LOGITS
     distribution
    3.50
     Distribution
    3.41
    Distribution
    3.39
    distribution
    3.23
     distributions
    3.09
     distribución
    3.03
     DISTRIBUTION
    3.03
     distribuição
    2.98
     distribuzione
    2.97
     Distributions
    2.94
    Activations Density 0.008%

    No Known Activations