© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144780
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ل
    1.25
    2
    1.21
    ី
    1.20
    told
    1.07
    ت
    1.07
    سال
    1.05
    ы
    1.05
     by
    1.04
    ip
    1.02
    tiin
    1.01
    POSITIVE LOGITS
    a
    1.53
    ุ
    1.53
    y
    1.52
    o
    1.51
    ع
    1.45
    e
    1.38
    ۰
    1.38
    ა
    1.37
    า
    1.32
    ing
    1.29
    Activations Density 0.000%

    No Known Activations