© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150780
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    了一
    1.20
    了一个
    1.20
     了
    1.07
    了一個
    1.05
    了一种
    1.02
    啦
    0.96
    了他
    0.94
    了吗
    0.93
    了我
    0.89
    了一些
    0.88
    POSITIVE LOGITS
    다
    1.16
    ا
    0.55
    و
    0.51
     छ
    0.50
     하다
    0.50
    า
    0.46
     var
    0.46
    하다
    0.45
    ard
    0.43
    jx
    0.43
    Activations Density 0.000%

    No Known Activations