© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259936
    Prev
    Next
    INDEX
    Explanations

    homes and property

    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_22_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
     pathological
    0.29
     insufficiency
    0.27
    نجليزية
    0.26
     circuitry
    0.25
     영어
    0.25
    ฝึก
    0.25
    कंप
    0.24
    語
    0.24
     stagger
    0.24
    ኹ
    0.24
    POSITIVE LOGITS
    azaar
    0.28
     આપે
    0.28
     suddenly
    0.25
     Gives
    0.25
     товаров
    0.25
     godiš
    0.24
    antar
    0.24
    簑
    0.24
    গি
    0.23
     Finally
    0.23
    Activations Density 0.000%

    No Known Activations