© 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. 195519
    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
     placeholders
    0.51
    חנו
    0.46
     playlists
    0.46
    otry
    0.45
    atient
    0.44
     plabic
    0.44
     autophagy
    0.43
    त
    0.43
    orghini
    0.43
     subpoenas
    0.43
    POSITIVE LOGITS
    国务
    0.49
     पिछले
    0.47
     ପ୍ର
    0.45
    ுள்ளார்
    0.45
    មក
    0.44
     තම
    0.44
     jueves
    0.44
     නමුත්
    0.44
     إلى
    0.42
     budú
    0.42
    Activations Density 0.000%

    No Known Activations