© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36126
    Prev
    Next
    INDEX
    Explanations

    single

    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_50_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
     સિ
    0.40
    ("-"*
    0.40
    रिज
    0.39
     Roj
    0.39
     Probe
    0.38
     মিসেস
    0.38
     عفوا
    0.38
    𝘣
    0.37
    ሉት
    0.36
    وتا
    0.36
    POSITIVE LOGITS
     đơn
    2.22
     yks
    2.05
    单
    2.05
    單
    2.00
     single
    1.98
     Single
    1.98
    Single
    1.92
    single
    1.87
     SINGLE
    1.80
     enkel
    1.74
    Activations Density 0.000%

    No Known Activations