© 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. 106250
    Prev
    Next
    INDEX
    Explanations

    properties of

    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
    2
    1.26
     is
    1.23
    1.22
    ٢
    1.09
    ای
    1.01
    к
    0.98
    s
    0.95
    ları
    0.90
    니
    0.89
    ς
    0.87
    POSITIVE LOGITS
    i
    1.77
    ي
    1.66
    י
    1.66
    t
    1.42
    ി
    1.30
    ת
    1.30
    い
    1.19
    ാ
    1.13
    ן
    1.12
    يقة
    1.08
    Activations Density 0.001%

    No Known Activations