© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_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
     contagion
    0.47
     confr
    0.46
     karma
    0.44
     standby
    0.43
    ilane
    0.43
    ྲ
    0.42
     Plex
    0.42
     decrees
    0.42
     foto
    0.41
     Pres
    0.41
    POSITIVE LOGITS
    iobium
    0.51
    靘
    0.51
    ड़ने
    0.50
    ாட
    0.48
    𝐣
    0.48
    ucksack
    0.48
    ற்ற
    0.47
    ipped
    0.47
    мерикан
    0.47
    𝐳
    0.47
    Activations Density 0.000%

    No Known Activations