© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51172
    Prev
    Next
    INDEX
    Explanations

    say "RGB"

    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_55_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
     R
    0.42
    лав
    0.41
    गंगा
    0.40
    squeeze
    0.39
     좋다
    0.39
     constraining
    0.39
    thermal
    0.38
     weddings
    0.38
     sınır
    0.38
    ()%
    0.37
    POSITIVE LOGITS
    Eg
    0.41
     Kau
    0.39
     MACHINE
    0.36
    室内
    0.36
     pink
    0.35
     Eg
    0.35
     asem
    0.35
     यूनिवर्सल
    0.34
     Hau
    0.34
     Argu
    0.34
    Activations Density 0.000%

    No Known Activations