© 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. 43663
    Prev
    Next
    INDEX
    Explanations

    Digital Ocean

    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
     nods
    0.14
     hassle
    0.14
    و
    0.13
    姆
    0.13
    ו
    0.13
     curtains
    0.13
     tackles
    0.12
    m
    0.12
     reels
    0.12
    ग
    0.12
    POSITIVE LOGITS
    íz
    0.14
    ī
    0.14
    foregroundView
    0.13
    according
    0.13
    ít
    0.13
     gyermek
    0.13
     withstand
    0.13
     使
    0.13
     使っ
    0.13
    做好
    0.12
    Activations Density 0.002%

    No Known Activations