© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202630
    Prev
    Next
    INDEX
    Explanations

    awkwardness

    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_46_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
     difficult
    0.39
     during
    0.39
     difficulties
    0.38
    name
    0.38
     difficulty
    0.37
    
    0.37
    oc
    0.37
    тре
    0.36
     divine
    0.36
    ®
    0.36
    POSITIVE LOGITS
    WAIT
    0.38
     száz
    0.38
     silenz
    0.38
     وە
    0.38
     Wait
    0.38
    Вот
    0.38
     Flush
    0.37
     egot
    0.37
     waitFor
    0.37
     czek
    0.37
    Activations Density 0.003%

    No Known Activations