© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157462
    Prev
    Next
    INDEX
    Explanations

    within reach

    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
     nara
    0.42
     indig
    0.40
     wür
    0.40
    氮
    0.39
     kv
    0.37
    altra
    0.36
     મા
    0.36
     છ
    0.36
     Nair
    0.36
     Duct
    0.36
    POSITIVE LOGITS
    оп
    0.44
    arching
    0.41
    обще
    0.40
    قر
    0.39
    atório
    0.39
    伸び
    0.39
    stretched
    0.38
     медици
    0.37
     Game
    0.37
    batches
    0.36
    Activations Density 0.000%

    No Known Activations