© 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. 195534
    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
    ole
    0.49
    ър
    0.45
    
    0.45
    ையில்
    0.44
    ادة
    0.43
    পুরে
    0.43
    mentar
    0.43
    ці
    0.42
    enta
    0.42
    ريكا
    0.42
    POSITIVE LOGITS
    و
    0.55
    морфи
    0.52
    Complaint
    0.52
    ButtonGroup
    0.51
    it
    0.50
    :
    0.50
    Communication
    0.49
    ب
    0.49
     safest
    0.48
    ุ
    0.48
    Activations Density 0.000%

    No Known Activations