© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213805
    Prev
    Next
    INDEX
    Explanations

    form labels

    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_50_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
     Locally
    0.45
     locally
    0.42
    ंची
    0.38
    璋
    0.38
    버
    0.37
    
    0.36
    ONES
    0.36
     ஊராட்சி
    0.36
    ޗ
    0.36
     इसकी
    0.36
    POSITIVE LOGITS
    মতে
    0.38
    ued
    0.38
     Dodson
    0.36
     dissipative
    0.35
     श्रेय
    0.35
    *}{
    0.35
    yzed
    0.35
     glances
    0.34
    Wise
    0.34
    зву
    0.34
    Activations Density 0.001%

    No Known Activations