© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163656
    Prev
    Next
    INDEX
    Explanations

    tissue growths or abnormal formations

    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_31_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
    সির
    0.36
     配置
    0.35
    緍
    0.34
    जेंट
    0.33
     மேற்கு
    0.33
     destruction
    0.33
    hint
    0.33
     Syrians
    0.32
     Париж
    0.32
     коктей
    0.32
    POSITIVE LOGITS
    叉
    0.38
    
    0.37
     হেতু
    0.36
    ји
    0.35
    ologous
    0.34
     دماغ
    0.34
    甾
    0.34
     অমন
    0.33
    외
    0.33
    lastCursor
    0.32
    Activations Density 0.004%

    No Known Activations