© 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. 103287
    Prev
    Next
    INDEX
    Explanations

    reviewing policies or data

    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
    ר
    1.16
    る
    1.13
     a
    0.86
    ת
    0.84
    ה
    0.83
    の開発
    0.81
    l
    0.79
    רים
    0.78
     sings
    0.77
    이었
    0.77
    POSITIVE LOGITS
    с
    1.07
        
    0.98
    os
    0.94
    v
    0.94
    س
    0.94
    ة
    0.94
    t
    0.90
    quela
    0.85
     to
    0.84
    ва
    0.82
    Activations Density 0.002%

    No Known Activations