© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 260161
    Prev
    Next
    INDEX
    Explanations

    press `F12` or `Alt+F11`

    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
     necessary
    0.21
     अध्यापक
    0.21
    に入
    0.21
     সেক্ষেত্রে
    0.21
    ：
    0.21
    ޓ
    0.20
    坑
    0.20
    ЕР
    0.20
    办理
    0.20
    以下
    0.20
    POSITIVE LOGITS
     komfort
    0.29
     zwięks
    0.28
    -}\
    0.25
    parvec
    0.24
    িন্দু
    0.24
     risultato
    0.23
     résultat
    0.23
     resultat
    0.23
    స్త్ర
    0.23
     넓
    0.22
    Activations Density 0.001%

    No Known Activations