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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198024
    Prev
    Next
    INDEX
    Explanations

    organizations and entities

    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
     फ्रा
    0.43
     Frans
    0.41
    PLICATION
    0.40
    Mark
    0.40
    <0x9F>
    0.38
     Frenchman
    0.38
    Mât
    0.38
    法语
    0.37
     ஜீய
    0.37
     フランス
    0.37
    POSITIVE LOGITS
    gar
    0.47
     nach
    0.44
     Elie
    0.43
    elk
    0.42
     bel
    0.41
     엘
    0.41
     David
    0.40
     henry
    0.40
     baits
    0.40
    सिर
    0.40
    Activations Density 0.006%

    No Known Activations