© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50877
    Prev
    Next
    INDEX
    Explanations

    html structure elements

    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_30_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
     illusion
    0.39
     actuaciones
    0.38
    льную
    0.37
    黏
    0.37
    品
    0.36
    illusion
    0.35
    View
    0.35
     খুল
    0.34
    AndView
    0.34
    Buying
    0.34
    POSITIVE LOGITS
    ตั้งแต่
    0.38
     silencing
    0.37
     iteration
    0.36
     কমান্ডার
    0.36
     Steady
    0.36
     namespaces
    0.36
    ɬ
    0.36
     recursion
    0.35
     ceasefire
    0.35
     estab
    0.35
    Activations Density 0.002%

    No Known Activations