© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202487
    Prev
    Next
    INDEX
    Explanations

    Universal Studios locations

    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_6_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
    د
    1.26
    ী
    1.13
    ہ
    1.04
    H
    1.02
    L
    0.99
    い
    0.94
    T
    0.92
    いっぱい
    0.88
    ު
    0.88
    ל
    0.87
    POSITIVE LOGITS
     is
    1.00
    ático
    0.89
    te
    0.85
     ശ്രദ്ധ
    0.85
     后
    0.84
    ka
    0.82
    orte
    0.81
    ft
    0.79
    ced
    0.79
    ли
    0.77
    Activations Density 0.000%

    No Known Activations