© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3565
    Prev
    Next
    INDEX
    Explanations

    method, invention, CN, TW, GB

    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_39_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
    Mead
    0.41
     armour
    0.38
    Vertex
    0.38
    мага
    0.38
     Scheidegg
    0.38
    Ù
    0.37
     Armor
    0.37
     plán
    0.37
     ड्राइ
    0.36
     vídeo
    0.36
    POSITIVE LOGITS
    ционных
    0.39
    滑
    0.38
    찐
    0.36
     CN
    0.35
     facilitated
    0.35
     smeared
    0.35
     टच
    0.35
     कॉम्प
    0.35
     Remix
    0.35
     eel
    0.34
    Activations Density 0.001%

    No Known Activations