© 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. 48553
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

    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
     d
    0.48
     i
    0.40
    、
    0.38
    late
    0.37
    H
    0.36
    ^
    0.36
    to
    0.36
    kan
    0.36
     y
    0.35
     b
    0.34
    POSITIVE LOGITS
     простых
    0.44
     ότι
    0.42
    ຜະລິດຕະພັນ
    0.40
    ﭥ
    0.40
     Игра
    0.40
    CreateCharacter
    0.39
     Acest
    0.39
     война
    0.39
    üş
    0.38
     Çünkü
    0.38
    Activations Density 0.007%

    No Known Activations