© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34451
    Prev
    Next
    INDEX
    Explanations

    mark titles and articles

    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
    ரி
    0.39
     pebb
    0.39
     Es
    0.36
    ricorn
    0.35
     NIN
    0.35
    ιστή
    0.35
     ris
    0.35
    呢
    0.35
     pela
    0.34
    మంది
    0.34
    POSITIVE LOGITS
     burnout
    0.45
     Doom
    0.39
    क्षे
    0.39
    Prova
    0.39
     সরকারী
    0.38
    Kui
    0.38
     Piping
    0.38
     कठिन
    0.37
     পাকিস্তানে
    0.37
    
    0.36
    Activations Density 0.004%

    No Known Activations