© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210949
    Prev
    Next
    INDEX
    Explanations

    Lewis, Day-, ACE

    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_5_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
    л
    1.05
    د
    0.96
     be
    0.92
     it
    0.86
     It
    0.86
    τή
    0.76
    ב
    0.75
     T
    0.74
    리
    0.74
    มัน
    0.74
    POSITIVE LOGITS
     типу
    0.68
    ﻣ
    0.61
     функция
    0.60
     уви
    0.58
    的海
    0.58
     ৫৮
    0.57
    的時間
    0.57
    的变化
    0.56
    ДИ
    0.55
    РЕ
    0.55
    Activations Density 0.000%

    No Known Activations