© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88967
    Prev
    Next
    INDEX
    Explanations

    dialogue writing

    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_23_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
     magnes
    0.44
     imper
    0.42
     permas
    0.42
    bron
    0.39
    宏
    0.39
    Imper
    0.39
    ごとに
    0.39
     cias
    0.38
    
    0.37
     calibr
    0.37
    POSITIVE LOGITS
    umoto
    0.39
    ői
    0.37
     Lol
    0.37
     ресурсов
    0.37
     textbooks
    0.37
     মানে
    0.36
     Harvest
    0.36
    texto
    0.35
     Arvind
    0.35
     Diversity
    0.35
    Activations Density 0.004%

    No Known Activations