© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242137
    Prev
    Next
    INDEX
    Explanations

    programming libraries import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     சாய
    0.40
    book
    0.39
    瑛
    0.38
    ory
    0.37
    کس
    0.37
    liest
    0.36
     TY
    0.35
    ชร์
    0.35
     mirror
    0.35
    ิบ
    0.35
    POSITIVE LOGITS
    ViewModels
    0.43
     Lieferung
    0.42
    ⎟
    0.41
     ViewData
    0.38
    蜻
    0.38
    MenuView
    0.36
     계약
    0.36
    viewModel
    0.36
     UnitTest
    0.36
     দেখুন
    0.35
    Activations Density 0.000%

    No Known Activations