© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33961
    Prev
    Next
    INDEX
    Explanations

    MA, M, Ma, MAR, Mac, Mach, Map, Mash

    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_31_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
    몫
    0.42
     factored
    0.37
     rallied
    0.36
     bior
    0.36
     Quartz
    0.36
     tritt
    0.35
     Repeating
    0.35
     Satan
    0.35
     Emper
    0.35
     Rally
    0.34
    POSITIVE LOGITS
    <0x90>
    0.59
     מא
    0.52
    Ма
    0.50
    MA
    0.49
     Ма
    0.49
    Ma
    0.48
     Ma
    0.46
    מא
    0.44
     麻
    0.43
    ma
    0.43
    Activations Density 0.043%

    No Known Activations