© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17147
    Prev
    Next
    INDEX
    Explanations

    google.com/edu/python

    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_15_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
    мет
    0.53
     exceeding
    0.47
    ت
    0.47
     serr
    0.47
    دق
    0.47
    继续
    0.45
     isEqual
    0.44
    포
    0.44
    डॉ
    0.43
     slotted
    0.43
    POSITIVE LOGITS
     दैट
    0.48
    ()]
    0.48
     состояния
    0.48
     വര്‍ഷ
    0.48
    besondere
    0.46
    ]=\
    0.45
    ModeBanner
    0.45
     svojoj
    0.45
     blau
    0.44
     warum
    0.43
    Activations Density 0.000%

    No Known Activations