© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158986
    Prev
    Next
    INDEX
    Explanations

    Korean, Thai, Chinese, English words

    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_2_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
    il
    1.05
    r
    1.05
    ة
    1.01
    𝗿
    0.98
    ர்
    0.98
    لها
    0.97
    that
    0.97
    ে
    0.96
    ing
    0.95
    то
    0.95
    POSITIVE LOGITS
    I
    1.25
    h
    1.17
    R
    1.09
     is
    1.01
    اً
    1.01
    D
    1.00
     has
    1.00
    og
    0.98
    B
    0.96
    ки
    0.95
    Activations Density 0.003%

    No Known Activations