© 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. 124692
    Prev
    Next
    INDEX
    Explanations

    supersonic, mach, aircraft

    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
    Dequeue
    0.38
     dichlor
    0.37
     pamo
    0.36
    рина
    0.35
     chlorophyll
    0.35
     bodys
    0.34
     pumps
    0.34
     _;
    0.34
     बाउ
    0.34
    กอง
    0.34
    POSITIVE LOGITS
     Mach
    0.43
    Overwrite
    0.42
    &=
    0.42
     overwrite
    0.41
    Mach
    0.39
     Action
    0.38
     document
    0.38
    MACH
    0.38
    action
    0.37
    document
    0.37
    Activations Density 0.001%

    No Known Activations