© 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. 213135
    Prev
    Next
    INDEX
    Explanations

    object instantiation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ดำเนิน
    0.43
     cus
    0.41
     रु
    0.40
    弥
    0.40
    Dan
    0.40
     Damon
    0.39
    Bachelor
    0.39
    螌
    0.39
    RectangleShape
    0.38
     kus
    0.38
    POSITIVE LOGITS
     Elisa
    0.42
    aisa
    0.42
     Elaina
    0.40
    elaide
    0.39
     Yards
    0.39
     Eliza
    0.39
     Elsa
    0.39
    crackers
    0.38
    illar
    0.38
     Leia
    0.38
    Activations Density 0.001%

    No Known Activations