© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195452
    Prev
    Next
    INDEX
    Explanations

    ung prefixes

    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_4_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
    ↵↵
    1.10
    то
    1.00
    ли
    0.97
    to
    0.96
    し
    0.96
     իր
    0.93
     immédi
    0.92
    p
    0.92
    j
    0.90
     у
    0.89
    POSITIVE LOGITS
    en
    1.04
    ar
    1.02
    et
    0.96
    o
    0.90
    ing
    0.89
    out
    0.86
    ا
    0.84
    an
    0.80
    as
    0.80
    ت
    0.79
    Activations Density 0.001%

    No Known Activations