© 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. 229788
    Prev
    Next
    INDEX
    Explanations

    data size and speed units

    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
    is
    1.13
    ig
    1.09
    in
    1.09
    un
    1.09
    am
    1.03
    ра
    1.01
    у
    0.99
    en
    0.98
    ли
    0.97
    um
    0.96
    POSITIVE LOGITS
    دی
    1.02
     are
    0.98
     وی
    0.96
    อายุ
    0.96
     ה
    0.96
    EST
    0.94
    ک
    0.93
     ببین
    0.89
    owań
    0.89
    Кто
    0.89
    Activations Density 0.000%

    No Known Activations