© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16791
    Prev
    Next
    INDEX
    Explanations

    @ means or equals

    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_15_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
    اله
    0.20
    ش
    0.19
    ال
    0.19
     към
    0.18
     Evaluation
    0.17
     evaluation
    0.17
    مان
    0.17
    ний
    0.17
    Elapsed
    0.17
    Moscow
    0.17
    POSITIVE LOGITS
    酆
    0.22
    हुन्छ
    0.21
    मूर्ति
    0.20
    uszcz
    0.20
    uyi
    0.20
    滸
    0.19
    ujte
    0.19
     hugely
    0.19
     pouches
    0.18
    ynu
    0.18
    Activations Density 0.038%

    No Known Activations