© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203254
    Prev
    Next
    INDEX
    Explanations

    following specific names/brands

    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_37_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
     milik
    0.43
    $.\
    0.42
    她的
    0.42
     hers
    0.40
     meiner
    0.40
    របស់
    0.39
    Mine
    0.38
    ibli
    0.38
     Mout
    0.37
     seiner
    0.36
    POSITIVE LOGITS
     скорее
    0.37
    ',{
    0.36
    ี่ยน
    0.35
     بنیاد
    0.35
    oku
    0.34
     வெளியில்
    0.34
     soport
    0.33
    əl
    0.33
     Zucker
    0.32
     товары
    0.32
    Activations Density 0.047%

    No Known Activations