© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196353
    Prev
    Next
    INDEX
    Explanations

    section titles or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     seconde
    0.41
    <unused56>
    0.40
     συνε
    0.39
    আমরা
    0.39
    垷
    0.38
     ಮತ್ತ
    0.38
     ಇನ್ನ
    0.38
     certains
    0.38
    RIER
    0.38
    啝
    0.37
    POSITIVE LOGITS
     disgust
    0.47
     Scandal
    0.36
     scathing
    0.36
     kul
    0.36
     Disk
    0.36
    uksen
    0.36
     Board
    0.36
     hijo
    0.35
     Stupid
    0.35
     fand
    0.35
    Activations Density 0.006%

    No Known Activations