© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132407
    Prev
    Next
    INDEX
    Explanations

    berg and gon suffixes

    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_1_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
    ش
    1.50
     to
    1.41
    是
    1.36
    ين
    1.31
    ע
    1.28
    يل
    1.24
    س
    1.23
    ع
    1.23
    ut
    1.23
    ق
    1.23
    POSITIVE LOGITS
    ੀ
    0.99
    stufe
    0.98
    nelly
    0.87
    स्पर
    0.82
     Hauser
    0.82
    тері
    0.81
    sembles
    0.81
    rette
    0.80
    мато
    0.79
    ים
    0.75
    Activations Density 0.000%

    No Known Activations