© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37999
    Prev
    Next
    INDEX
    Explanations

    names of organizations and places

    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_11_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
    >
    0.47
    **
    0.47
    ร
    0.46
    ป
    0.46
    อาหาร
    0.43
    �
    0.41
    ?"
    0.40
     די
    0.40
     if
    0.39
    ="../../../../
    0.39
    POSITIVE LOGITS
    klassen
    0.47
     koju
    0.47
     பண்டைய
    0.46
     Faktoren
    0.45
    ರಳ
    0.45
    ků
    0.45
     koja
    0.44
     која
    0.43
    کا
    0.43
    каў
    0.43
    Activations Density 0.001%

    No Known Activations