© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203318
    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_37_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
    නි
    0.40
     thawing
    0.39
    噉
    0.39
    ราะ
    0.36
     resumed
    0.36
     psycho
    0.36
     enctype
    0.36
    න්
    0.36
     resume
    0.36
     elsif
    0.36
    POSITIVE LOGITS
    asjoner
    0.40
    aturan
    0.39
    ble
    0.38
    郎
    0.37
    resser
    0.37
    Adams
    0.37
    pore
    0.36
     Adams
    0.36
    FEN
    0.36
     brigade
    0.36
    Activations Density 0.000%

    No Known Activations