© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261002
    Prev
    Next
    INDEX
    Explanations

    dig, DiGeorge, digerir

    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_5_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
    ur
    1.42
    I
    1.31
    re
    1.22
    هم
    1.02
    al
    1.01
    p
    0.99
    com
    0.99
    ar
    0.97
    S
    0.97
    ра
    0.95
    POSITIVE LOGITS
    ة
    1.27
    ק
    1.14
     oppure
    1.00
    ına
    0.95
    ৬
    0.89
    GEN
    0.89
    ა
    0.89
    ing
    0.88
     інші
    0.85
    ిన
    0.83
    Activations Density 0.000%

    No Known Activations