© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99611
    Prev
    Next
    INDEX
    Explanations

    ever the

    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_16_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
    𝘆
    0.47
    𝗶
    0.46
    uciones
    0.45
    ත්තේ
    0.45
     শ্রীমতি
    0.45
    
    0.45
    莗
    0.44
    𝕝
    0.44
     כי
    0.44
    徃
    0.44
    POSITIVE LOGITS
    Steam
    0.54
    Utility
    0.54
     are
    0.52
    Parent
    0.52
    Kin
    0.52
    Dis
    0.50
    2
    0.49
    GD
    0.48
    Solar
    0.48
    Con
    0.47
    Activations Density 0.000%

    No Known Activations