© 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. 177738
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ᄇ
    0.39
    AddNew
    0.38
     kepad
    0.38
    .-(
    0.37
     "-"
    0.37
     clav
    0.37
    Klein
    0.37
     maxn
    0.37
     नाइट्रोजन
    0.36
    ेष
    0.36
    POSITIVE LOGITS
     Holly
    0.40
     holy
    0.40
     hole
    0.39
     हो
    0.39
     sonic
    0.38
    霍
    0.38
    荷
    0.38
     hol
    0.38
     হল
    0.37
    ૧
    0.37
    Activations Density 0.002%

    No Known Activations