© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51979
    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_30_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
    
    0.43
    сунок
    0.37
     позна
    0.37
    선
    0.37
     তিনটি
    0.36
     পাঁচটি
    0.36
     والدین
    0.36
    父母
    0.36
    沿
    0.35
     licenc
    0.35
    POSITIVE LOGITS
    fj
    0.39
    antlr
    0.36
    ହି
    0.36
    Cog
    0.35
    छि
    0.35
     uncontroll
    0.35
    ترى
    0.35
     QnrB
    0.35
    pena
    0.35
     Appl
    0.34
    Activations Density 0.000%

    No Known Activations