© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137556
    Prev
    Next
    INDEX
    Explanations

    say "2G", "3G", "4G"

    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
     G
    0.82
    G
    0.60
    Ｇ
    0.45
     ग
    0.43
    Gs
    0.42
     Go
    0.40
     Dean
    0.40
    𝐺
    0.40
    dR
    0.39
    GO
    0.39
    POSITIVE LOGITS
     génération
    0.55
     générations
    0.54
     generaciones
    0.47
     generations
    0.44
     generation
    0.43
    generation
    0.43
    Generation
    0.42
    BottomSheet
    0.42
     पीढ़ी
    0.41
    阁
    0.40
    Activations Density 0.002%

    No Known Activations