© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257410
    Prev
    Next
    INDEX
    Explanations

    defining classes and structures

    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
    BusinessType
    0.39
    Thickness
    0.38
     attenuated
    0.37
    xc
    0.36
     configured
    0.36
    ୀ
    0.36
    配置
    0.36
    XC
    0.35
     ছি
    0.35
    кты
    0.35
    POSITIVE LOGITS
     powerplant
    0.49
     nightlife
    0.47
    躋
    0.45
    চের
    0.45
     muziek
    0.45
    说到
    0.45
     supercar
    0.44
     যানবাহ
    0.42
     उभर
    0.42
     Venice
    0.42
    Activations Density 0.001%

    No Known Activations