© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223658
    Prev
    Next
    INDEX
    Explanations

    for

    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_10_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
    ي
    0.66
    ة
    0.61
    ن
    0.57
    ávy
    0.54
     angered
    0.54
    ás
    0.53
     conseguido
    0.53
    ac
    0.52
     diffused
    0.51
     relâche
    0.51
    POSITIVE LOGITS
    ۳
    0.58
    А
    0.56
    ۹
    0.54
    ۵
    0.53
    ("[
    0.51
    Α
    0.51
    X
    0.50
    Q
    0.50
    ג
    0.50
     aplikasi
    0.49
    Activations Density 0.035%

    No Known Activations