© 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. 203339
    Prev
    Next
    INDEX
    Explanations

    Chinese and Hindi characters

    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
     висо
    0.84
    _
    0.83
     funktion
    0.81
     он
    0.80
     forts
    0.80
     博文
    0.77
     he
    0.75
     t
    0.73
     техни
    0.71
     brine
    0.71
    POSITIVE LOGITS
    أ
    1.16
    म
    1.03
    سی
    1.02
    ों
    1.01
    ल
    1.01
    不
    0.99
    는
    0.99
    は
    0.98
    さ
    0.96
    ד
    0.96
    Activations Density 0.002%

    No Known Activations