© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134920
    Prev
    Next
    INDEX
    Explanations

    Niro, Cro, Ramos, Rocha, Gama

    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_1_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
    iy
    1.16
     $
    1.03
    ิ
    1.02
     избра
    1.01
    িক
    0.99
    ired
    0.99
     X
    0.96
    ě
    0.95
    ти
    0.94
    ěl
    0.91
    POSITIVE LOGITS
    在
    1.71
    的
    1.57
    人
    1.50
    '
    1.43
    不
    1.42
    沒有
    1.31
    會
    1.30
    可以
    1.27
    过
    1.25
    好
    1.23
    Activations Density 0.001%

    No Known Activations