© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80891
    Prev
    Next
    INDEX
    Explanations

    W

    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_53_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
    Hir
    0.44
     HIR
    0.43
    ِه
    0.41
    рма
    0.40
     지
    0.39
     hereinafter
    0.39
     Hir
    0.39
    anaa
    0.39
     coat
    0.39
    Edward
    0.38
    POSITIVE LOGITS
     кол
    0.40
     Regen
    0.38
     Ке
    0.38
    㑼
    0.38
    دار
    0.37
     Feuer
    0.37
     советы
    0.36
    uccio
    0.36
    浈
    0.35
     sheer
    0.35
    Activations Density 0.006%

    No Known Activations