© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20677
    Prev
    Next
    INDEX
    Explanations

    bible verses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    IFORN
    0.36
    고사
    0.35
    
    0.34
    㑒
    0.34
    십시오
    0.34
    ॉर्क
    0.33
    当たり
    0.32
     solvers
    0.32
    ༡
    0.31
    Supp
    0.31
    POSITIVE LOGITS
     പ്രതീ
    0.38
    ֛
    0.38
    owy
    0.37
    ֑
    0.37
    বিদ্য
    0.36
    急性
    0.35
     निर्देशित
    0.35
    ֤
    0.35
    iy
    0.34
     Provence
    0.34
    Activations Density 0.002%

    No Known Activations