© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198707
    Prev
    Next
    INDEX
    Explanations

    height

    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
    uzen
    0.40
    وبت
    0.38
     Whitman
    0.38
     besar
    0.37
    suc
    0.36
     ανα
    0.36
    र्मेंद्र
    0.35
    朴
    0.35
    ｿ
    0.35
     Pleasure
    0.34
    POSITIVE LOGITS
     jokes
    0.43
     mistaken
    0.43
     Jokes
    0.43
    jokes
    0.41
     mistakes
    0.40
     जिद
    0.40
     высокие
    0.40
    Bl
    0.39
    Circ
    0.38
    ffield
    0.38
    Activations Density 0.006%

    No Known Activations