© 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. 27280
    Prev
    Next
    INDEX
    Explanations

    application request

    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
     explorar
    0.50
     employs
    0.48
     his
    0.47
     continuar
    0.45
    弼
    0.45
     acrob
    0.44
     contain
    0.43
    ير
    0.43
     winning
    0.43
     be
    0.43
    POSITIVE LOGITS
    &=&
    0.52
    اتج
    0.50
    #$%
    0.48
    जिद
    0.47
    ↴
    0.47
    нали
    0.46
     (\%)
    0.45
    Ⅼ
    0.45
    rizioni
    0.44
    headphones
    0.44
    Activations Density 0.000%

    No Known Activations