© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11889
    Prev
    Next
    INDEX
    Explanations

    acts of kindness or service

    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_13_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
    ъ
    0.58
    ="
    0.51
     el
    0.50
     живо
    0.47
     הזה
    0.45
    ancio
    0.45
    릿
    0.45
     υ
    0.44
    thats
    0.44
     medicamento
    0.44
    POSITIVE LOGITS
    šan
    0.53
    setDefault
    0.53
    electrode
    0.53
     Swindon
    0.52
    spirit
    0.52
     Бер
    0.51
     Marianne
    0.51
    cheek
    0.51
     MFG
    0.50
    iterator
    0.50
    Activations Density 0.036%

    No Known Activations