© 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. 16885
    Prev
    Next
    INDEX
    Explanations

    these

    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
    ແລະ
    0.51
    _{(\
    0.50
    both
    0.48
    ⦕
    0.48
     TMN
    0.48
    笾
    0.48
    ignés
    0.47
     FODC
    0.47
     paramètres
    0.46
    幵
    0.46
    POSITIVE LOGITS
    ضا
    0.52
     prostitution
    0.50
     victimization
    0.49
     clout
    0.49
     charter
    0.48
     flaw
    0.47
    linearity
    0.47
     systemic
    0.46
    ルの
    0.45
     prostit
    0.45
    Activations Density 0.008%

    No Known Activations