© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68291
    Prev
    Next
    INDEX
    Explanations

    eyes and faces

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     AFP
    0.41
    AFP
    0.40
    മ്പോൾ
    0.39
    loose
    0.38
    idak
    0.38
    Sn
    0.38
    Af
    0.38
    瑜
    0.36
     सलू
    0.36
    这件事
    0.35
    POSITIVE LOGITS
     зе
    0.64
    зе
    0.57
     зи
    0.56
     Зе
    0.56
     ze
    0.53
     زي
    0.50
     ZE
    0.47
     bâ
    0.46
     Ze
    0.45
    зей
    0.45
    Activations Density 0.001%

    No Known Activations