© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203352
    Prev
    Next
    INDEX
    Explanations

    infused plate, MachSpeed technology, Zoom cushioning

    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_37_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
     ogranic
    0.42
     चंद
    0.42
     Lept
    0.42
    чник
    0.41
     derive
    0.38
     chand
    0.38
    鸞
    0.38
     गहराई
    0.37
     Sonya
    0.37
     deriving
    0.37
    POSITIVE LOGITS
     കാ
    0.38
    шали
    0.35
     MARIA
    0.34
     binary
    0.34
    ਣੀ
    0.34
     expresses
    0.34
     алы
    0.34
    代
    0.33
     modes
    0.33
     incorporation
    0.33
    Activations Density 0.000%

    No Known Activations