© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36541
    Prev
    Next
    INDEX
    Explanations

    android widget or Android Auto

    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_3_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
    that
    0.82
    は
    0.70
    𝑺
    0.64
    do
    0.61
    Kết
    0.59
    ない
    0.59
    really
    0.59
    ﻮ
    0.59
    should
    0.58
    娌
    0.58
    POSITIVE LOGITS
     from
    0.83
     for
    0.81
     at
    0.80
     API
    0.73
    م
    0.71
    ہ
    0.70
     system
    0.68
     usur
    0.67
     sim
    0.64
     traduc
    0.64
    Activations Density 0.001%

    No Known Activations