© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203308
    Prev
    Next
    INDEX
    Explanations

    boxed answer

    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_6_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
    at
    0.95
    ed
    0.95
    al
    0.89
    ли
    0.85
    м
    0.84
    то
    0.81
    ot
    0.74
    es
    0.73
    емых
    0.71
    ل
    0.71
    POSITIVE LOGITS
     enzymes
    0.98
     neutrons
    0.80
     vitamins
    0.80
     patents
    0.80
     glands
    0.79
     is
    0.76
     infections
    0.75
     approvals
    0.75
    ки
    0.74
     chemicals
    0.74
    Activations Density 0.002%

    No Known Activations