© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221150
    Prev
    Next
    INDEX
    Explanations

    efficiency, safety, principle

    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_10_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
    یز
    0.57
    گوید
    0.54
    सिला
    0.50
    έσ
    0.49
    یک
    0.49
    ه‌ای
    0.48
    ่า
    0.48
    앓
    0.47
    یم
    0.47
    რავ
    0.47
    POSITIVE LOGITS
     amerikan
    0.59
     n
    0.55
    يين
    0.50
     langen
    0.50
     jungen
    0.49
     lau
    0.49
     ganó
    0.49
     d
    0.48
     dieses
    0.48
    បន្ថែម
    0.48
    Activations Density 0.000%

    No Known Activations